{"total":94,"rows":[{"id":"2303.08112","title":"Eliciting Latent Predictions from Transformers with the Tuned Lens","created":"2023-03-14","cited_by_count":623,"area":"mechinterp"},{"id":"2404.14082","title":"Mechanistic Interpretability for AI Safety -- A Review","created":"2024-04-22","cited_by_count":422,"area":"mechinterp"},{"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":"2401.06102","title":"Patchscopes: A Unifying Framework for Inspecting Hidden Representations of Language Models","created":"2024-01-11","cited_by_count":235,"area":"mechinterp"},{"id":"2407.02646","title":"A Practical Review of Mechanistic Interpretability for Transformer-Based Language Models","created":"2024-07-02","cited_by_count":118,"area":"mechinterp"},{"id":"2406.00034","title":"Adaptive Activation Steering: A Tuning-Free LLM Truthfulness Improvement Method for Diverse Hallucinations Categories","created":"2024-05-26","cited_by_count":77,"area":"mechinterp"},{"id":"2503.05613","title":"A Survey on Sparse Autoencoders: Interpreting the Internal Mechanisms of Large Language Models","created":"2025-03-07","cited_by_count":76,"area":"mechinterp"},{"id":"2306.01128","title":"Learning Transformer Programs","created":"2023-06-01","cited_by_count":41,"area":"mechinterp"},{"id":"2507.08802","title":"The Non-Linear Representation Dilemma: Is Causal Abstraction Enough for Mechanistic Interpretability?","created":"2025-07-11","cited_by_count":37,"area":"mechinterp"},{"id":"2502.11356","title":"SAIF: A Sparse Autoencoder Framework for Interpreting and Steering Instruction Following of Language Models","created":"2025-02-17","cited_by_count":34,"area":"mechinterp"},{"id":"2411.04430","title":"Towards Unifying Interpretability and Control: Evaluation via Intervention","created":"2024-11-07","cited_by_count":32,"area":"mechinterp"},{"id":"2503.02080","title":"Linear Representations of Political Perspective Emerge in Large Language Models","created":"2025-03-03","cited_by_count":32,"area":"mechinterp"},{"id":"2604.28119","title":"Do Sparse Autoencoders Capture Concept Manifolds?","created":"2026-04-30","cited_by_count":31,"area":"mechinterp"},{"id":"2505.16188","title":"SAE-SSV: Supervised Steering in Sparse Representation Spaces for Reliable Control of Language Models","created":"2025-05-22","cited_by_count":29,"area":"mechinterp"},{"id":"2511.00617","title":"Belief Dynamics Reveal the Dual Nature of In-Context Learning and Activation Steering","created":"2025-11-01","cited_by_count":29,"area":"mechinterp"},{"id":"2502.05489","title":"Mechanistic Interpretability of Emotion Inference in Large Language Models","created":"2025-02-08","cited_by_count":27,"area":"mechinterp"},{"id":"2601.14004","title":"Locate, Steer, and Improve: A Practical Survey of Actionable Mechanistic Interpretability in Large Language Models","created":"2026-01-20","cited_by_count":27,"area":"mechinterp"},{"id":"2407.19200","title":"On Behalf of the Stakeholders: Trends in NLP Model Interpretability in the Era of LLMs","created":"2024-07-27","cited_by_count":25,"area":"mechinterp"},{"id":"2410.09087","title":"Mechanistic?","created":"2024-10-07","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":"2502.17601","title":"Representation Engineering for Large-Language Models: Survey and Research Challenges","created":"2025-02-24","cited_by_count":21,"area":"mechinterp"},{"id":"2506.23845","title":"Position: Use Sparse Autoencoders to Discover Unknowns","created":"2025-06-30","cited_by_count":19,"area":"mechinterp"},{"id":"2411.00743","title":"Decoding Dark Matter: Specialized Sparse Autoencoders for Interpreting Rare Concepts in Foundation Models","created":"2024-11-01","cited_by_count":16,"area":"mechinterp"},{"id":"2509.13316","title":"Do Activation Verbalization Methods Convey Privileged Information?","created":"2025-09-16","cited_by_count":10,"area":"mechinterp"},{"id":"2511.21399","title":"Steering Awareness: Detecting Activation Steering from Within","created":"2025-11-26","cited_by_count":9,"area":"mechinterp"},{"id":"2602.06964","title":"Learning a Generative Meta-Model of LLM Activations","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2504.08001","title":"Linguistic Interpretability of Transformer-based Language Models: a systematic review","created":"2025-04-09","cited_by_count":7,"area":"mechinterp"},{"id":"2506.04706","title":"Line of Sight: On Linear Representations in VLLMs","created":"2025-06-05","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":"2604.02608","title":"Steerable but Not Decodable: Function Vectors Operate Beyond the Logit Lens","created":"2026-04-03","cited_by_count":6,"area":"mechinterp"},{"id":"2607.07003","title":"Dissociating the Internal Representations of Sycophancy in LLMs","created":"2026-07-08","cited_by_count":6,"area":"mechinterp"},{"id":"2605.13930","title":"Mechanistic Interpretability of EEG Foundation Models via Sparse Autoencoders","created":"2026-05-13","cited_by_count":5,"area":"mechinterp"},{"id":"2407.13594","title":"Validating Mechanistic Interpretations: An Axiomatic Approach","created":"2024-07-18","cited_by_count":4,"area":"mechinterp"},{"id":"2508.17320","title":"AdaptiveK: Complexity-Driven Sparse Autoencoders for Interpretable Language Model Representations","created":"2025-08-24","cited_by_count":4,"area":"mechinterp"},{"id":"2602.08159","title":"The Confidence Manifold: Geometric Structure of Correctness Representations in Language Models","created":"2026-02-08","cited_by_count":4,"area":"mechinterp"},{"id":"2604.15557","title":"Predicting Where Steering Vectors Succeed","created":"2026-04-16","cited_by_count":4,"area":"mechinterp"},{"id":"2503.02078","title":"Superscopes: Amplifying Internal Feature Representations for Language Model Interpretation","created":"2025-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2505.16612","title":"Steering Large Language Models for Machine Translation Personalization","created":"2025-05-22","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":"2510.01048","title":"Interpreting Language Models Through Concept Descriptions: A Survey","created":"2025-10-01","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":"2602.09783","title":"Why Linear Interpretability Works: Invariant Subspaces as a Result of Architectural Constraints","created":"2026-02-10","cited_by_count":3,"area":"mechinterp"},{"id":"2604.13466","title":"Functional Emotions or Situational Contexts? A Discriminating Test from the Mythos Preview System Card","created":"2026-04-09","cited_by_count":3,"area":"mechinterp"},{"id":"2504.13763","title":"Decoding Vision Transformers: the Diffusion Steering Lens","created":"2025-04-18","cited_by_count":2,"area":"mechinterp"},{"id":"2505.03368","title":"Geospatial Mechanistic Interpretability of Large Language Models","created":"2025-05-06","cited_by_count":2,"area":"mechinterp"},{"id":"2508.04530","title":"Balancing Stylization and Truth via Disentangled Representation Steering","created":"2025-08-06","cited_by_count":2,"area":"mechinterp"},{"id":"2510.09794","title":"Causality $\\neq$ Decodability, and Vice Versa: Lessons from Interpreting Counting ViTs","created":"2025-10-10","cited_by_count":2,"area":"mechinterp"},{"id":"2602.17229","title":"Mechanistic Interpretability of Cognitive Complexity in LLMs via Linear Probing using Bloom's Taxonomy","created":"2026-02-19","cited_by_count":2,"area":"mechinterp"},{"id":"2603.17624","title":"Do Language Models Encode Semantic Relations? Probing and Sparse Feature Analysis","created":"2026-03-18","cited_by_count":2,"area":"mechinterp"},{"id":"2604.13068","title":"Detection Without Correction: A Robust Asymmetry in Activation-Based Hallucination Probing","created":"2026-03-20","cited_by_count":2,"area":"mechinterp"},{"id":"2606.00033","title":"Make Mechanistic Interpretability Auditable: A Call to Develop Guidelines via Continuous Collaborative Reviewing","created":"2026-04-24","cited_by_count":2,"area":"mechinterp"},{"id":"2606.08792","title":"The Amplifying Mirror: Locating and Steering the Partisan Direction inside a Large Language Model","created":"2026-06-07","cited_by_count":2,"area":"mechinterp"},{"id":"2609.18080","title":"Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition","created":"2026-09-16","cited_by_count":2,"area":"mechinterp"},{"id":"2506.12576","title":"Calibrating Lightweight Sparse Autoencoder Feature Steering","created":"2025-06-14","cited_by_count":1,"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":"2511.18409","title":"Findings of the BlackboxNLP 2025 Shared Task: Localizing Circuits and Causal Variables in Language Models","created":"2025-11-23","cited_by_count":1,"area":"mechinterp"},{"id":"2601.03464","title":"Prompting Underestimates LLM Capability for Time Series Classification","created":"2026-01-06","cited_by_count":1,"area":"mechinterp"},{"id":"2601.22818","title":"Hide and Seek in Embedding Space: Geometry-based Steganography and Detection in Large Language Models","created":"2026-01-30","cited_by_count":1,"area":"mechinterp"},{"id":"2602.09784","title":"Circuit Fingerprints: How Answer Tokens Encode Their Geometrical Path","created":"2026-02-10","cited_by_count":1,"area":"mechinterp"},{"id":"2602.13524","title":"Singular Vectors of Attention Heads Align with Features","created":"2026-02-13","cited_by_count":1,"area":"mechinterp"},{"id":"2603.18893","title":"Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation","created":"2026-03-19","cited_by_count":1,"area":"mechinterp"},{"id":"2606.19603","title":"Comparing Linear Probes with Mahalanobis Cosine Similarity","created":"2026-06-17","cited_by_count":1,"area":"mechinterp"},{"id":"2608.07528","title":"The Knowing-Saying Gap: When Probes See Errors that Confidence Misses","created":"2026-07-21","cited_by_count":1,"area":"mechinterp"},{"id":"2608.24988","title":"Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal","created":"2026-08-25","cited_by_count":1,"area":"mechinterp"},{"id":"2609.08250","title":"CALIPER: Clean Scenes Cannot Rank Physical Inference in Pretrained Visual Representations","created":"2026-09-08","cited_by_count":1,"area":"mechinterp"},{"id":"2609.22135","title":"Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models","created":"2026-08-24","cited_by_count":1,"area":"mechinterp"},{"id":"2502.15090","title":"ExpertLens: Activation steering features are highly interpretable","created":"2025-02-20","cited_by_count":0,"area":"mechinterp"},{"id":"2505.02154","title":"Interpreting Multilingual and Document-Length Sensitive Relevance Computations in Neural Retrieval Models through Axiomatic Causal Interventions","created":"2025-05-04","cited_by_count":0,"area":"mechinterp"},{"id":"2506.04774","title":"Fine-Grained Interpretation of Political Opinions in Large Language Models","created":"2025-06-05","cited_by_count":0,"area":"mechinterp"},{"id":"2512.19734","title":"The Deleuzian Representation Hypothesis","created":"2025-12-17","cited_by_count":0,"area":"mechinterp"},{"id":"2601.22928","title":"LLMs Explain't: A Post-Mortem on Semantic Interpretability in Transformer Models","created":"2026-01-30","cited_by_count":0,"area":"mechinterp"},{"id":"2602.03506","title":"Explaining the Explainer: Understanding the Inner Workings of Transformer-based Symbolic Regression Models","created":"2026-02-03","cited_by_count":0,"area":"mechinterp"},{"id":"2605.06303","title":"Molecules Meet Language: Confound-Aware Representation Learning and Chemical Property Steering in Transformer-VAE Latent Spaces","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.20824","title":"Markovian Circuit Tracing for Transformer State Dynamic","created":"2026-05-20","cited_by_count":0,"area":"mechinterp"},{"id":"2606.20152","title":"From Texts to Scores: Tracing the Emergence of Essay Quality Representations in Large Language Models","created":"2026-06-18","cited_by_count":0,"area":"mechinterp"},{"id":"2606.32008","title":"Surrogate Fidelity: When Can Open LLMs Explain Closed Ones?","created":"2026-06-30","cited_by_count":0,"area":"mechinterp"},{"id":"2607.25459","title":"Emergent Latent-State Computation under Stochastic Volatility","created":"2026-07-28","cited_by_count":0,"area":"mechinterp"},{"id":"2608.02486","title":"Cultural Awareness is Represented but Not Decoded: Tracing Mythological Knowledge across 18 Open-Source LLMs","created":"2026-08-03","cited_by_count":0,"area":"mechinterp"},{"id":"2608.02957","title":"Inverted Detection and Control in Steering Vectors","created":"2026-08-03","cited_by_count":0,"area":"mechinterp"},{"id":"2608.05160","title":"The Ignition Index: Measuring Global Workspace Dynamics in Language Models","created":"2026-05-26","cited_by_count":0,"area":"mechinterp"},{"id":"2608.06638","title":"MI-MIDI: Mechanistic Interpretability of Text-to-MIDI Generation Models via Probing, Lenses and Steering","created":"2026-08-06","cited_by_count":0,"area":"mechinterp"},{"id":"2608.07208","title":"Measuring Concept Content in Text from LLM Activations: ESG Evidence from Concept Vectors and Linear Probes","created":"2026-08-07","cited_by_count":0,"area":"mechinterp"},{"id":"2608.24780","title":"Linear Probing Provides Robust and Efficient Detection of Machine-Generated Text","created":"2026-08-25","cited_by_count":0,"area":"mechinterp"},{"id":"2609.01048","title":"Lagged Coupling: Internal Representations Become Readable Before They Become Causal","created":"2026-09-01","cited_by_count":0,"area":"mechinterp"},{"id":"2609.09902","title":"Contrastive Projection: Reading Transformer Internals by Differencing Logit Lenses","created":"2026-09-09","cited_by_count":0,"area":"mechinterp"},{"id":"2609.18533","title":"A Probe Shift Is Not a Fairness Fix: The Limits of Representation Steering in Speech Models","created":"2026-09-16","cited_by_count":0,"area":"mechinterp"},{"id":"2609.25021","title":"\"As a Language Model...\": Chat Template Switches LLM Self-Referential Voice and Activation Steering Reproduces It","created":"2026-08-09","cited_by_count":0,"area":"mechinterp"},{"id":"2609.29362","title":"Parts-of-Speech as Emergent Categories in SAE Latent Space","created":"2026-09-24","cited_by_count":0,"area":"mechinterp"},{"id":"2609.37680","title":"When Models Don't Manipulate Manifolds: The Geometry of a Comparison Task","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2609.37857","title":"Active Budget Can Kill Sensitivity: Diagnosing and Repairing TopK Sparse Autoencoder Reliability","created":"2026-09-29","cited_by_count":0,"area":"mechinterp"},{"id":"2610.02829","title":"Clinical Concept Centers in LLMs","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"},{"id":"2610.05577","title":"What Does an Observability Foundation Model Know?","created":"2026-10-04","cited_by_count":0,"area":"mechinterp"},{"id":"2610.15850","title":"What Do Sparse Autoencoder Feature Discovery Scores Identify? From Activations to Interventions","created":"2026-10-11","cited_by_count":0,"area":"mechinterp"},{"id":"2610.19359","title":"Steering Vectors for Competing Ethical Frameworks Are Interchangeable: A Competing-Target Test for Activation Steering","created":"2026-10-14","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}