{"total":200,"rows":[{"id":"2408.05147","title":"Gemma Scope: Open Sparse Autoencoders Everywhere All At Once on Gemma 2","created":"2024-08-09","cited_by_count":394,"area":"mechinterp"},{"id":"2605.29358","title":"Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet","created":"2026-05-28","cited_by_count":191,"area":"mechinterp"},{"id":"2410.20526","title":"Llama Scope: Extracting Millions of Features from Llama-3.1-8B with Sparse Autoencoders","created":"2024-10-27","cited_by_count":143,"area":"mechinterp"},{"id":"2412.05563","title":"A Survey on Uncertainty Quantification of Large Language Models: Taxonomy, Open Research Challenges, and Future Directions","created":"2024-12-07","cited_by_count":121,"area":null},{"id":"2607.15495","title":"Verbalizable Representations Form a Global Workspace in Language Models","created":"2026-07-16","cited_by_count":75,"area":null},{"id":"2503.01822","title":"Projecting Assumptions: The Duality Between Sparse Autoencoders and Concept Geometry","created":"2025-03-03","cited_by_count":61,"area":"mechinterp"},{"id":"2604.07729","title":"Emotion Concepts and their Function in a Large Language Model","created":"2026-04-09","cited_by_count":57,"area":null},{"id":"2407.15017","title":"Knowledge Mechanisms in Large Language Models: A Survey and Perspective","created":"2024-07-22","cited_by_count":51,"area":null},{"id":"2601.04480","title":"When Models Manipulate Manifolds: The Geometry of a Counting Task","created":"2026-01-08","cited_by_count":46,"area":null},{"id":"2511.13653","title":"Weight-sparse transformers have interpretable circuits","created":"2025-11-17","cited_by_count":44,"area":"mechinterp"},{"id":"2603.05488","title":"Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought","created":"2026-03-05","cited_by_count":40,"area":"lr"},{"id":"2506.18183","title":"Reasoning about Uncertainty: Do Reasoning Models Know When They Don't Know?","created":"2025-06-22","cited_by_count":38,"area":"lr"},{"id":"2502.20914","title":"Everything, Everywhere, All at Once: Is Mechanistic Interpretability Identifiable?","created":"2025-02-28","cited_by_count":34,"area":"mechinterp"},{"id":"2504.02922","title":"Overcoming Sparsity Artifacts in Crosscoders to Interpret Chat-Tuning","created":"2025-04-03","cited_by_count":34,"area":null},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32,"area":"mechinterp"},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","cited_by_count":25,"area":"mechinterp"},{"id":"2601.22594","title":"Language Model Circuits Are Sparse in the Neuron Basis","created":"2026-01-30","cited_by_count":25,"area":"mechinterp"},{"id":"2408.01416","title":"The Quest for the Right Mediator: Surveying Mechanistic Interpretability Through the Lens of Causal Mediation Analysis","created":"2024-08-02","cited_by_count":24,"area":"mechinterp"},{"id":"2409.15318","title":"On the Complexity of Neural Computation in Superposition","created":"2024-09-05","cited_by_count":21,"area":"mechinterp"},{"id":"2504.19475","title":"Prisma: An Open Source Toolkit for Mechanistic Interpretability in Vision and Video","created":"2025-04-28","cited_by_count":21,"area":"mechinterp"},{"id":"2605.11887","title":"Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models","created":"2026-05-12","cited_by_count":21,"area":"mechinterp"},{"id":"2409.04185","title":"Residual Stream Analysis with Multi-Layer SAEs","created":"2024-09-06","cited_by_count":19,"area":"mechinterp"},{"id":"2501.15638","title":"A Comprehensive Survey on Self-Interpretable Neural Networks","created":"2025-01-26","cited_by_count":18,"area":null},{"id":"2510.00845","title":"Mechanistic Interpretability as Statistical Estimation: A Variance Analysis","created":"2025-10-01","cited_by_count":15,"area":"mechinterp"},{"id":"2506.01197","title":"Incorporating Hierarchical Semantics in Sparse Autoencoder Architectures","created":"2025-06-01","cited_by_count":14,"area":"mechinterp"},{"id":"2602.14111","title":"Sanity Checks for Sparse Autoencoders: Do SAEs Beat Random Baselines?","created":"2026-02-15","cited_by_count":14,"area":"mechinterp"},{"id":"2502.03032","title":"Analyze Feature Flow to Enhance Interpretation and Steering in Language Models","created":"2025-02-05","cited_by_count":13,"area":"mechinterp"},{"id":"2504.14379","title":"The Geometry of Self-Verification in a Task-Specific Reasoning Model","created":"2025-04-19","cited_by_count":13,"area":"lr"},{"id":"2508.20279","title":"How Multimodal LLMs Solve Image Tasks: A Lens on Visual Grounding, Task Reasoning, and Answer Decoding","created":"2025-08-27","cited_by_count":13,"area":"lr"},{"id":"2505.16004","title":"Evaluating Adversarial Robustness of Concept Representations in Sparse Autoencoders","created":"2025-05-21","cited_by_count":12,"area":"mechinterp"},{"id":"2512.18792","title":"The Dead Salmons of AI Interpretability","created":"2025-12-21","cited_by_count":12,"area":null},{"id":"2512.24440","title":"Towards mechanistic understanding in a data-driven weather model: internal activations reveal interpretable physical features","created":"2025-12-30","cited_by_count":12,"area":null},{"id":"2502.00837","title":"Explainability in Practice: A Survey of Explainable NLP Across Various Domains","created":"2025-02-02","cited_by_count":11,"area":null},{"id":"2509.02565","title":"Understanding sparse autoencoder scaling in the presence of feature manifolds","created":"2025-09-02","cited_by_count":11,"area":"mechinterp"},{"id":"2602.16823","title":"Formal Mechanistic Interpretability: Automated Circuit Discovery with Provable Guarantees","created":"2026-02-18","cited_by_count":11,"area":"mechinterp"},{"id":"2502.18147","title":"Jacobian Sparse Autoencoders: Sparsify Computations, Not Just Activations","created":"2025-02-25","cited_by_count":10,"area":"mechinterp"},{"id":"2507.00711","title":"Large Reasoning Models are not thinking straight: on the unreliability of thinking trajectories","created":"2025-07-01","cited_by_count":10,"area":"lr"},{"id":"2504.08842","title":"Towards Combinatorial Interpretability of Neural Computation","created":"2025-04-10","cited_by_count":9,"area":null},{"id":"2504.20938","title":"Towards Understanding the Nature of Attention with Low-Rank Sparse Decomposition","created":"2025-04-29","cited_by_count":9,"area":"mechinterp"},{"id":"2505.14071","title":"Textual Steering Vectors Can Improve Visual Understanding in Multimodal Large Language Models","created":"2025-05-20","cited_by_count":9,"area":"mllm"},{"id":"2604.02605","title":"Do Audio-Visual Large Language Models Really See and Hear?","created":"2026-04-03","cited_by_count":9,"area":null},{"id":"2508.01916","title":"Decomposing Representation Space into Interpretable Subspaces with Unsupervised Learning","created":"2025-08-03","cited_by_count":8,"area":"mechinterp"},{"id":"2509.17196","title":"Evolution of Concepts in Language Model Pre-Training","created":"2025-09-21","cited_by_count":8,"area":null},{"id":"2509.25758","title":"Thinking Sparks!: Emergent Attention Heads in Reasoning Models During Post Training","created":"2025-09-30","cited_by_count":8,"area":"lr"},{"id":"2511.10840","title":"Tracing Multilingual Representations in LLMs with Cross-Layer Transcoders","created":"2025-11-13","cited_by_count":8,"area":"mechinterp"},{"id":"2602.20330","title":"Circuit Tracing in Vision-Language Models: Understanding the Internal Mechanisms of Multimodal Thinking","created":"2026-02-23","cited_by_count":8,"area":"lr"},{"id":"2604.03976","title":"Quantifying Trust: Financial Risk Management for Trustworthy AI Agents","created":"2026-04-05","cited_by_count":8,"area":null},{"id":"2512.08892","title":"Toward Faithful Retrieval-Augmented Generation with Sparse Autoencoders","created":"2025-12-09","cited_by_count":7,"area":"rag"},{"id":"2603.21396","title":"Mechanisms of Introspective Awareness","created":"2026-03-22","cited_by_count":7,"area":"mechinterp"},{"id":"2604.02178","title":"The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level","created":"2026-04-02","cited_by_count":7,"area":"moe"},{"id":"2605.00842","title":"Understanding Emergent Misalignment via Feature Superposition Geometry","created":"2026-04-07","cited_by_count":7,"area":"mechinterp"},{"id":"2608.02657","title":"Your Agentic LLMs Secretly Encode Indirect Prompt-Injection Exposure in Hidden States","created":"2026-08-01","cited_by_count":7,"area":"agents"},{"id":"2506.18141","title":"Sparse Feature Coactivation Reveals Causal Semantic Modules in Large Language Models","created":"2025-06-22","cited_by_count":6,"area":"mechinterp"},{"id":"2508.16929","title":"Dimensional Collapse in Transformer Attention Outputs: A Challenge for Sparse Dictionary Learning","created":"2025-08-23","cited_by_count":6,"area":"mechinterp"},{"id":"2511.19265","title":"Unboxing the Black Box: Mechanistic Interpretability for Algorithmic Understanding of Neural Networks","created":"2025-11-24","cited_by_count":6,"area":"mechinterp"},{"id":"2602.22554","title":"Multilingual Safety Alignment Via Sparse Weight Editing","created":"2026-02-26","cited_by_count":6,"area":"alignment"},{"id":"2604.12493","title":"Latent Planning Emerges with Scale","created":"2026-04-14","cited_by_count":6,"area":null},{"id":"2605.19091","title":"Chessformer: A Unified Architecture for Chess Modeling","created":"2026-05-18","cited_by_count":6,"area":null},{"id":"2504.13756","title":"Scaling sparse feature circuit finding for in-context learning","created":"2025-04-18","cited_by_count":5,"area":"mechinterp"},{"id":"2505.21364","title":"Towards Interpretability Without Sacrifice: Faithful Dense Layer Decomposition with Mixture of Decoders","created":"2025-05-27","cited_by_count":5,"area":null},{"id":"2509.12934","title":"The Anatomy of Alignment: Decomposing Preference Optimization by Steering Sparse Features","created":"2025-09-16","cited_by_count":5,"area":"alignment"},{"id":"2510.14936","title":"Circuit Insights: Towards Interpretability Beyond Activations","created":"2025-10-16","cited_by_count":5,"area":"mechinterp"},{"id":"2511.03878","title":"KnowThyself: An Agentic Assistant for LLM Interpretability","created":"2025-11-05","cited_by_count":5,"area":"agents"},{"id":"2602.14697","title":"Evolutionary System Prompt Learning for Reinforcement Learning in LLMs","created":"2026-02-16","cited_by_count":5,"area":"agents"},{"id":"2605.05668","title":"Large Vision-Language Models Get Lost in Attention","created":"2026-05-07","cited_by_count":5,"area":"mllm"},{"id":"2605.24279","title":"ContextEcho: A Benchmark for Persona Drift in Long Agentic-Coding Sessions","created":"2026-05-22","cited_by_count":5,"area":"agents"},{"id":"2505.11611","title":"Signal in the Noise: Polysemantic Interference Transfers and Predicts Cross-Model Influence","created":"2025-05-16","cited_by_count":4,"area":"mechinterp"},{"id":"2506.01042","title":"Probing Neural Topology of Large Language Models","created":"2025-06-01","cited_by_count":4,"area":null},{"id":"2506.10138","title":"Path Channels and Plan Extension Kernels: a Mechanistic Description of Planning in a Sokoban RNN","created":"2025-06-11","cited_by_count":4,"area":"deeprl"},{"id":"2509.23717","title":"Measuring Sparse Autoencoder Feature Sensitivity","created":"2025-09-28","cited_by_count":4,"area":"mechinterp"},{"id":"2512.05865","title":"Intrinsically Interpretable Attention via Sparse Post-Training","created":"2025-12-05","cited_by_count":4,"area":null},{"id":"2605.07922","title":"Tree SAE: Learning Hierarchical Feature Structures in Sparse Autoencoders","created":"2026-05-08","cited_by_count":4,"area":"mechinterp"},{"id":"2607.08349","title":"Certified Interventional Fidelity: Anytime-Valid, Adaptive Evaluation of Causal Claims in Mechanistic Interpretability","created":"2026-07-09","cited_by_count":4,"area":"mechinterp"},{"id":"2607.12474","title":"From Observation to Insight: Mechanistic World Models and the Quest for Autonomous Discovery","created":"2026-07-14","cited_by_count":4,"area":"wm"},{"id":"2505.11189","title":"Can Global XAI Methods Reveal Injected Behaviours in LLMs? SHAP vs Rule Extraction vs RuleSHAP","created":"2025-05-16","cited_by_count":3,"area":null},{"id":"2505.17769","title":"Inference-Time Decomposition of Activations (ITDA): A Scalable Approach to Interpreting Large Language Models","created":"2025-05-23","cited_by_count":3,"area":"mechinterp"},{"id":"2509.25045","title":"Hyperdimensional Probe: Decoding LLM Representations via Vector Symbolic Architectures","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2509.25596","title":"Binary Sparse Coding for Interpretability","created":"2025-09-29","cited_by_count":3,"area":"mechinterp"},{"id":"2512.05534","title":"A Unified Theory of Sparse Dictionary Learning in Mechanistic Interpretability: Piecewise Biconvexity and Spurious Minima","created":"2025-12-05","cited_by_count":3,"area":"mechinterp"},{"id":"2602.01322","title":"PolySAE: Modeling Feature Interactions in Sparse Autoencoders via Polynomial Decoding","created":"2026-02-01","cited_by_count":3,"area":"mechinterp"},{"id":"2602.07080","title":"CodeCircuit: Toward Inferring LLM-Generated Code Correctness via Attribution Graphs","created":"2026-02-06","cited_by_count":3,"area":null},{"id":"2602.12026","title":"Protein Circuit Tracing via Cross-layer Transcoders","created":"2026-02-12","cited_by_count":3,"area":"mechinterp"},{"id":"2606.09658","title":"Muon Learns More Robust and Transferable Features than Adam","created":"2026-06-08","cited_by_count":3,"area":null},{"id":"2606.15796","title":"DifFRACT: Diffusion Feature Reconstruction and Attribution for Circuit Tracing","created":"2026-06-14","cited_by_count":3,"area":"diffusion"},{"id":"2609.07876","title":"LLM Layers Immediately Correct Each Other","created":"2026-09-07","cited_by_count":3,"area":"mechinterp"},{"id":"2502.05242","title":"Beyond External Monitors: Enhancing Transparency of Large Language Models for Easier Monitoring","created":"2025-02-07","cited_by_count":2,"area":null},{"id":"2505.12268","title":"$K$-MSHC: Unmasking Minimally Sufficient Head Circuits in Large Language Models with Experiments on Syntactic Classification Tasks","created":"2025-05-18","cited_by_count":2,"area":"mechinterp"},{"id":"2506.20040","title":"Cross-Layer Discrete Concept Discovery for Interpreting Language Models","created":"2025-06-24","cited_by_count":2,"area":"mechinterp"},{"id":"2509.20124","title":"Probability Signature: Bridging Data Semantics and Embedding Structure in Language Models","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2510.00034","title":"Review of Hallucination Understanding in Large Language and Vision Models","created":"2025-09-26","cited_by_count":2,"area":null},{"id":"2510.06378","title":"Semantic Regexes: Auto-Interpreting LLM Features with a Structured Language","created":"2025-10-07","cited_by_count":2,"area":null},{"id":"2510.21464","title":"CXR-LanIC: Language-Grounded Interpretable Classifier for Chest X-Ray Diagnosis","created":"2025-10-24","cited_by_count":2,"area":null},{"id":"2511.20910","title":"Emergence and Localisation of Semantic Role Circuits in LLMs","created":"2025-11-25","cited_by_count":2,"area":"mechinterp"},{"id":"2512.09757","title":"Circuits, Features, and Heuristics in Molecular Transformers","created":"2025-12-10","cited_by_count":2,"area":"mechinterp"},{"id":"2601.11019","title":"Finding the Translation Switch: Discovering and Exploiting the Task-Initiation Features in LLMs","created":"2026-01-16","cited_by_count":2,"area":"mechinterp"},{"id":"2603.01879","title":"Diagnosing Generalization Failures from Representational Geometry Markers","created":"2026-03-02","cited_by_count":2,"area":null},{"id":"2603.21014","title":"CLT-Forge: A Scalable Library for Cross-Layer Transcoders and Attribution Graphs","created":"2026-03-22","cited_by_count":2,"area":"mechinterp"},{"id":"2604.10158","title":"Tracing the Thought of a Grandmaster-level Chess-Playing Transformer","created":"2026-04-11","cited_by_count":2,"area":null},{"id":"2604.17761","title":"Contrastive Attribution in the Wild: An Interpretability Analysis of LLM Failures on Realistic Benchmarks","created":"2026-04-20","cited_by_count":2,"area":"mechinterp"},{"id":"2605.03354","title":"What Happens Inside Agent Memory? Circuit Analysis from Emergence to Diagnosis","created":"2026-05-05","cited_by_count":2,"area":"agents"}],"next_cursor":"100"}