{"total":93,"rows":[{"id":"2502.12892","title":"Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Models","created":"2025-02-18","cited_by_count":73,"area":"mechinterp"},{"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":"2502.20578","title":"Interpreting CLIP with Hierarchical Sparse Autoencoders","created":"2025-02-27","cited_by_count":60,"area":"mechinterp"},{"id":"2504.11695","title":"Interpreting the linear structure of vision-language model embedding spaces","created":"2025-04-16","cited_by_count":32,"area":"mllm"},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2510.07364","title":"Base Models Know How to Reason, Thinking Models Learn When","created":"2025-10-08","cited_by_count":27,"area":"lr"},{"id":"2506.06609","title":"Transferring Linear Features Across Language Models With Model Stitching","created":"2025-06-07","cited_by_count":21,"area":"mechinterp"},{"id":"2511.05541","title":"Temporal Sparse Autoencoders: Leveraging the Sequential Nature of Language for Interpretability","created":"2025-10-30","cited_by_count":18,"area":"mechinterp"},{"id":"2503.01824","title":"From superposition to sparse codes: interpretable representations in neural networks","created":"2025-03-03","cited_by_count":16,"area":null},{"id":"2505.20254","title":"Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs","created":"2025-05-26","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":"2503.08764","title":"Towards Interpretable Protein Structure Prediction with Sparse Autoencoders","created":"2025-03-11","cited_by_count":12,"area":"mechinterp"},{"id":"2602.11246","title":"How Many Features Can a Language Model Store Under the Linear Representation Hypothesis?","created":"2026-02-11","cited_by_count":12,"area":null},{"id":"2506.19382","title":"Measuring and Guiding Monosemanticity","created":"2025-06-24","cited_by_count":10,"area":"mechinterp"},{"id":"2503.24277","title":"Evaluating and Designing Sparse Autoencoders by Approximating Quasi-Orthogonality","created":"2025-03-31","cited_by_count":8,"area":"mechinterp"},{"id":"2507.06445","title":"Can Interpretation Predict Behavior on Unseen Data?","created":"2025-07-08","cited_by_count":8,"area":null},{"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":"2504.12939","title":"Disentangling Polysemantic Channels in Convolutional Neural Networks","created":"2025-04-17","cited_by_count":6,"area":"mechinterp"},{"id":"2603.28744","title":"Stop Probing, Start Coding: Why Linear Probes and Sparse Autoencoders Fail at Compositional Generalisation","created":"2026-03-30","cited_by_count":6,"area":"mechinterp"},{"id":"2502.06809","title":"Neurons Speak in Ranges: Breaking Free from Discrete Neuronal Attribution","created":"2025-02-04","cited_by_count":5,"area":null},{"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":"2510.16820","title":"Finding Manifolds With Bilinear Autoencoders","created":"2025-10-19","cited_by_count":5,"area":"mechinterp"},{"id":"2603.04198","title":"Stable and Steerable Sparse Autoencoders with Weight Regularization","created":"2026-03-04","cited_by_count":5,"area":"mechinterp"},{"id":"2603.13249","title":"Steering at the Source: Style Modulation Heads for Robust Persona Control","created":"2026-02-24","cited_by_count":5,"area":"mechinterp"},{"id":"2606.03002","title":"Perplexity Can Miss SAE Feature Damage Under Quantization","created":"2026-06-02","cited_by_count":5,"area":"mechinterp"},{"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":"2510.00468","title":"Feature Identification via the Empirical NTK","created":"2025-10-01","cited_by_count":4,"area":null},{"id":"2510.03186","title":"Superposition disentanglement of neural representations reveals hidden alignment","created":"2025-10-03","cited_by_count":4,"area":"mechinterp"},{"id":"2512.24975","title":"Attribution-Guided Distillation of Matryoshka Sparse Autoencoders","created":"2025-12-31","cited_by_count":4,"area":"mechinterp"},{"id":"2602.15829","title":"Operationalising the Superficial Alignment Hypothesis via Task Complexity","created":"2026-02-17","cited_by_count":4,"area":null},{"id":"2605.18229","title":"Are Sparse Autoencoder Benchmarks Reliable?","created":"2026-05-18","cited_by_count":4,"area":"mechinterp"},{"id":"2505.16077","title":"Ensembling Sparse Autoencoders","created":"2025-05-21","cited_by_count":3,"area":"mechinterp"},{"id":"2508.09363","title":"Resurrecting the Salmon: Rethinking Mechanistic Interpretability with Domain-Specific Sparse Autoencoders","created":"2025-08-12","cited_by_count":3,"area":"lr"},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2602.05184","title":"Towards Worst-Case Guarantees with Scale-Aware Interpretability","created":"2026-02-05","cited_by_count":3,"area":null},{"id":"2605.12991","title":"Not Just RLHF: Why Alignment Alone Won't Fix Multi-Agent Sycophancy","created":"2026-05-13","cited_by_count":3,"area":"agents"},{"id":"2605.31183","title":"Steering LLMs? Actually, Sparse Autoencoders can outperform simple baselines","created":"2026-05-29","cited_by_count":3,"area":"mechinterp"},{"id":"2606.06533","title":"Position: Don't Just \"Fix it in Post\": A Science of AI Must Study Training Dynamics","created":"2026-06-03","cited_by_count":3,"area":null},{"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":"2506.20040","title":"Cross-Layer Discrete Concept Discovery for Interpreting Language Models","created":"2025-06-24","cited_by_count":2,"area":"mechinterp"},{"id":"2507.00163","title":"Prompting as Scientific Inquiry","created":"2025-06-30","cited_by_count":2,"area":null},{"id":"2510.25807","title":"Discovering Interpretable Biological Concepts in Single-cell RNA-seq Foundation Models","created":"2025-10-29","cited_by_count":2,"area":null},{"id":"2511.06048","title":"Visual Exploration of Feature Relationships in Sparse Autoencoders with Curated Concepts","created":"2025-11-08","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":"2602.04718","title":"Superposition Without Interference? Towards Isolated Interventions via Almost Orthogonal Features in Language Models","created":"2026-02-04","cited_by_count":2,"area":"mechinterp"},{"id":"2605.12874","title":"Descriptive Collision in Sparse Autoencoder Auto-Interpretability: When One Explanation Describes Many Features","created":"2026-05-13","cited_by_count":2,"area":"mechinterp"},{"id":"2605.31245","title":"Toward Identifiable Sparse Autoencoders","created":"2026-05-29","cited_by_count":2,"area":"mechinterp"},{"id":"2508.15841","title":"A Review of Developmental Interpretability in Large Language Models","created":"2025-08-19","cited_by_count":1,"area":"mechinterp"},{"id":"2511.17735","title":"Towards Open-Ended Visual Scientific Discovery with Sparse Autoencoders","created":"2025-11-21","cited_by_count":1,"area":"mechinterp"},{"id":"2512.06655","title":"Graph-Regularized Sparse Autoencoders for LLM Safety Steering","created":"2025-12-07","cited_by_count":1,"area":"safety"},{"id":"2512.15938","title":"SALVE: Sparse Autoencoder-Latent Vector Editing for Mechanistic Control of Neural Networks","created":"2025-12-17","cited_by_count":1,"area":"mechinterp"},{"id":"2604.24936","title":"A Unifying Framework for Unsupervised Concept Extraction","created":"2026-04-27","cited_by_count":1,"area":"mechinterp"},{"id":"2605.08891","title":"Bilinear autoencoders find interpretable manifolds","created":"2026-05-09","cited_by_count":1,"area":"mechinterp"},{"id":"2605.12770","title":"WriteSAE: Sparse Autoencoders for Recurrent State","created":"2026-05-12","cited_by_count":1,"area":"ssm"},{"id":"2605.18629","title":"Aligned Training: A Parameter-Free Method to Improve Feature Quality and Stability of Sparse Autoencoders (SAE)","created":"2026-05-18","cited_by_count":1,"area":"mechinterp"},{"id":"2606.02061","title":"Ablating Archetypes: The Stability of Archetypal SAEs is an Artifact of Initialization and Metric Design","created":"2026-06-01","cited_by_count":1,"area":"mechinterp"},{"id":"2606.31963","title":"Signed-Permutation Coordinate Transport for RMSNorm Transformers","created":"2026-06-30","cited_by_count":1,"area":"mechinterp"},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","cited_by_count":1,"area":"mechinterp"},{"id":"2609.01936","title":"Sparse Readout Prism: Explaining Logit-Lens Scores in Features Instead of Tokens","created":"2026-09-01","cited_by_count":1,"area":null},{"id":"2505.22255","title":"Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2506.21468","title":"TopK Language Models","created":"2025-06-26","cited_by_count":0,"area":"mechinterp"},{"id":"2508.21324","title":"Distribution-Aware Feature Selection for SAEs","created":"2025-08-29","cited_by_count":0,"area":"mechinterp"},{"id":"2509.22015","title":"Concept-SAE: A Controllable and Invertible Concept Interface for Sparse Autoencoders","created":"2025-09-26","cited_by_count":0,"area":"mechinterp"},{"id":"2511.09178","title":"Perspectives on a Reliability Monitoring Framework for Agentic AI Systems","created":"2025-11-12","cited_by_count":0,"area":"agents"},{"id":"2512.20638","title":"Uncovering Competency Gaps in Large Language Models and Their Benchmarks","created":"2025-12-06","cited_by_count":0,"area":null},{"id":"2602.10508","title":"Med-SegLens: Latent-Level Model Diffing for Interpretable Medical Image Segmentation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2604.00208","title":"Similarity of Neural Network Representations in Superposition","created":"2026-03-31","cited_by_count":0,"area":"mechinterp"},{"id":"2605.04072","title":"Sparse Autoencoder Decomposition of Clinical Sequence Model Representations: Feature Complexity, Task Specialisation, and Mortality Prediction","created":"2026-04-13","cited_by_count":0,"area":"mechinterp"},{"id":"2605.14347","title":"Exemplar Partitioning for Mechanistic Interpretability","created":"2026-05-14","cited_by_count":0,"area":"safety"},{"id":"2605.28149","title":"Sign-Aware Gated Sparse Autoencoders: Modeling Anticorrelated Features with Bi-Jump-ReLU Activations","created":"2026-05-27","cited_by_count":0,"area":"mechinterp"},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.14040","title":"Decompose Sparsely Where You Should, Absorb Densely Where You Should No","created":"2026-06-12","cited_by_count":0,"area":"mechinterp"},{"id":"2606.26396","title":"At the Edge of Understanding: Sparse Autoencoders Trace The Limits of Transformer Generalization","created":"2026-06-24","cited_by_count":0,"area":"mechinterp"},{"id":"2607.03365","title":"Brand-as-Memory: Vision-Language Models Encode Causal, Mechanistically Localizable Credibility Priors for News Sources","created":"2026-07-03","cited_by_count":0,"area":"mllm"},{"id":"2607.19386","title":"Building Fast, Evaluating Slow: Pipeline Choices Dominate Autointerpretability Score Variance","created":"2026-07-01","cited_by_count":0,"area":"mechinterp"},{"id":"2608.13337","title":"Where You Measure Decides What You Measure: Position Selection in Ablation-Based SAE Evaluation","created":"2026-08-13","cited_by_count":0,"area":"mechinterp"},{"id":"2608.26090","title":"Finding and using interpretable latents in a neutrino foundation model with sparse autoencoders","created":"2026-08-26","cited_by_count":0,"area":"mechinterp"},{"id":"2608.27754","title":"Efficient Auto-Interpretability of AI Models in Biology","created":"2026-08-27","cited_by_count":0,"area":"mechinterp"},{"id":"2608.28924","title":"Causal Interventions Reveal Typologically Organized Syntactic Mechanisms in Multilingual Language Models","created":"2026-08-28","cited_by_count":0,"area":null},{"id":"2608.29034","title":"A Unifying Perspective on Language Model Representations: From Filler-Role Structure to Mechanistic Interpretability","created":"2026-08-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.12591","title":"Where Decoder Cosine Similarity Fails for SAE Feature Flow Discovery","created":"2026-09-11","cited_by_count":0,"area":"mechinterp"},{"id":"2609.15533","title":"The Misery of Mechanistic Interpretability: A Formal Perspective","created":"2026-09-14","cited_by_count":0,"area":"mechinterp"},{"id":"2609.35020","title":"Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2609.35890","title":"Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Training","created":"2026-09-27","cited_by_count":0,"area":"mechinterp"},{"id":"2609.36294","title":"When Trees Are Not Enough: Learning Mixed-Topology Feature Graphs with Adaptive Graph Sparse Autoencoders","created":"2026-09-28","cited_by_count":0,"area":"mechinterp"},{"id":"2609.39625","title":"D-Scope: Decomposing and Steering Diffusion Transformers with Sparse Autoencoders","created":"2026-09-30","cited_by_count":0,"area":"diffusion"},{"id":"2610.02829","title":"Clinical Concept Centers in LLMs","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"},{"id":"2610.03109","title":"Emergent Structure in the Marginal Attention Space of Language Models","created":"2026-10-02","cited_by_count":0,"area":null},{"id":"2610.04020","title":"ClasSAE: Class-Aligned Sparse Autoencoders via Differentiable Feature-Class Affinity","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"},{"id":"2610.05794","title":"A Testable Theory of Atomic Features","created":"2026-10-05","cited_by_count":0,"area":"mechinterp"},{"id":"2610.12989","title":"Language Models Have Interpretable Narrative Mechanisms","created":"2026-10-09","cited_by_count":0,"area":null},{"id":"2610.17093","title":"SFT Leaves a Reproducible Signature in Activation Geometry: Calibrating Post-Training Interpretability Against Run-to-Run Noise","created":"2026-10-12","cited_by_count":0,"area":null}],"next_cursor":null}