{"total":43,"rows":[{"id":"2504.13151","title":"MIB: A Mechanistic Interpretability Benchmark","created":"2025-04-17","cited_by_count":56,"area":"mechinterp"},{"id":"2505.10465","title":"Superposition Yields Robust Neural Scaling","created":"2025-05-15","cited_by_count":31,"area":"mechinterp"},{"id":"2505.05111","title":"Unveiling Language-Specific Features in Large Language Models via Sparse Autoencoders","created":"2025-05-08","cited_by_count":13,"area":"mechinterp"},{"id":"2503.06269","title":"Using Mechanistic Interpretability to Craft Adversarial Attacks against Large Language Models","created":"2025-03-08","cited_by_count":10,"area":"mechinterp"},{"id":"2510.03659","title":"Does higher interpretability imply better utility? A Pairwise Analysis on Sparse Autoencoders","created":"2025-10-04","cited_by_count":10,"area":"mechinterp"},{"id":"2508.17621","title":"Steering When Necessary: Flexible Steering Large Language Models with Backtracking","created":"2025-08-25","cited_by_count":8,"area":"mechinterp"},{"id":"2602.06801","title":"On the Non-Identifiability of Steering Vectors in Large Language Models","created":"2026-02-06","cited_by_count":8,"area":"mechinterp"},{"id":"2510.22256","title":"SteerX: Disentangled Steering for LLM Personalization","created":"2025-10-25","cited_by_count":7,"area":"mechinterp"},{"id":"2604.24693","title":"Contextual Linear Activation Steering of Language Models","created":"2026-04-27","cited_by_count":7,"area":"mechinterp"},{"id":"2601.05437","title":"Tracing Moral Foundations in Large Language Models","created":"2026-01-09","cited_by_count":6,"area":"mechinterp"},{"id":"2603.02237","title":"Concept Heterogeneity-aware Representation Steering","created":"2026-02-13","cited_by_count":6,"area":"mechinterp"},{"id":"2605.10664","title":"Prompt-Activation Duality: Improving Activation Steering via Attention-Level Interventions","created":"2026-05-11","cited_by_count":6,"area":"mechinterp"},{"id":"2507.12990","title":"Teach Old SAEs New Domain Tricks with Boosting","created":"2025-07-17","cited_by_count":5,"area":"mechinterp"},{"id":"2606.22357","title":"ORBIT: Training-Free Multi-Attribute Behavioral Steering via Orthogonal Subspace Rotation","created":"2026-06-21","cited_by_count":4,"area":"mechinterp"},{"id":"2607.16821","title":"First-Order Predictable but Pairwise Fragile: Local Task Adaptation in Trained Transformers","created":"2026-07-18","cited_by_count":4,"area":"mechinterp"},{"id":"2606.02628","title":"Hallucination Is Linearly Decodable from Mid-Layer Hidden States in Quantized LLMs","created":"2026-05-30","cited_by_count":3,"area":"mechinterp"},{"id":"2507.14894","title":"SASFT: Sparse Autoencoder-guided Supervised Finetuning to Mitigate Unexpected Code-Switching in LLMs","created":"2025-07-20","cited_by_count":2,"area":"mechinterp"},{"id":"2604.13694","title":"Weight Patching: Toward Source-Level Mechanistic Localization in LLMs","created":"2026-04-15","cited_by_count":2,"area":"mechinterp"},{"id":"2605.09129","title":"Data-driven Circuit Discovery for Interpretability of Language Models","created":"2026-05-09","cited_by_count":2,"area":"mechinterp"},{"id":"2608.19338","title":"Mechanistic Tomography: Designed Measurement for Control-Oriented Interpretability","created":"2026-08-19","cited_by_count":2,"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":"2603.18893","title":"Quantitative Introspection in Language Models: Tracking Emotive States Across Conversation","created":"2026-03-19","cited_by_count":1,"area":"mechinterp"},{"id":"2606.01695","title":"CANARY: Zero-Label Detection of Fine-Tuning Contamination in Language Models","created":"2026-06-01","cited_by_count":1,"area":"mechinterp"},{"id":"2606.28548","title":"Turn-Averaged SAEs for Feature Discovery and Long-Context Attribution","created":"2026-06-26","cited_by_count":1,"area":"mechinterp"},{"id":"2608.22985","title":"What Does Activation Steering Control? Attribution Across Answer Encodings and Output-Sensitive Subspaces","created":"2026-08-24","cited_by_count":1,"area":"mechinterp"},{"id":"2608.24335","title":"SteerCheck: Attribution Specificity and Alignment Leakage in Activation-Steering Audits","created":"2026-08-25","cited_by_count":1,"area":"mechinterp"},{"id":"2609.03026","title":"ObserverBench: Testing Mechanistic Estimates for Intervention and Control","created":"2026-09-02","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":"2505.22255","title":"Kronecker Factorization Improves Efficiency and Interpretability of Sparse Autoencoders","created":"2025-05-28","cited_by_count":0,"area":"mechinterp"},{"id":"2604.18179","title":"Committed SAE-Feature Traces for Audited-Session Substitution Detection in Hosted LLMs","created":"2026-04-20","cited_by_count":0,"area":"mechinterp"},{"id":"2605.05653","title":"Negative Before Positive: Asymmetric Valence Processing in Large Language Models","created":"2026-05-07","cited_by_count":0,"area":"mechinterp"},{"id":"2605.08853","title":"Architecture, Not Scale: Circuit Localization in Large Language Models","created":"2026-05-09","cited_by_count":0,"area":"mechinterp"},{"id":"2606.09287","title":"Trajectory Geometry of Transformer Representations Across Layers","created":"2026-06-08","cited_by_count":0,"area":"mechinterp"},{"id":"2607.01799","title":"Expander Sparse Autoencoders: Parameter-Efficient Dictionaries for Mechanistic Interpretability","created":"2026-07-02","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":"2608.30986","title":"Controlling Refusal Behavior of LLMs via Stiefel-Constrained Rotation Steering","created":"2026-08-31","cited_by_count":0,"area":"mechinterp"},{"id":"2609.06473","title":"Steering Under Compression: Dose-Response, Capability Cost, and Failure Asymmetry in Quantized LLMs","created":"2026-09-06","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":"2609.16967","title":"Target-Language Generation in Multilingual Models: Activation Steering and Optimal Control","created":"2026-09-15","cited_by_count":0,"area":"mechinterp"},{"id":"2609.33810","title":"Controlling Speaking Rate in Autoregressive TTS via Activation Steering","created":"2026-09-27","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":"2609.39243","title":"Right Answer, Wrong Mechanism: Detecting Pernicious Divergence in Causal Interventions","created":"2026-09-30","cited_by_count":0,"area":"mechinterp"}],"next_cursor":null}