{"total":73,"rows":[{"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":"2506.03093","title":"From Flat to Hierarchical: Extracting Sparse Representations with Matching Pursuit","created":"2025-06-03","cited_by_count":49,"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":"2605.05115","title":"Manifold Steering Reveals the Shared Geometry of Neural Network Representation and Behavior","created":"2026-05-06","cited_by_count":26,"area":null},{"id":"2512.19941","title":"Block-Recurrent Dynamics in Vision Transformers","created":"2025-12-23","cited_by_count":20,"area":null},{"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":"2505.20254","title":"Position: Mechanistic Interpretability Should Prioritize Feature Consistency in SAEs","created":"2025-05-26","cited_by_count":14,"area":"mechinterp"},{"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":"2602.06218","title":"Cross-Modal Redundancy and the Geometry of Vision-Language Embeddings","created":"2026-02-05","cited_by_count":10,"area":"mllm"},{"id":"2504.12392","title":"A Survey on Archetypal Analysis","created":"2025-04-16","cited_by_count":6,"area":null},{"id":"2512.10805","title":"Interpretable and Steerable Concept Bottleneck Sparse Autoencoders","created":"2025-12-11","cited_by_count":6,"area":"mechinterp"},{"id":"2506.02204","title":"BehaviorBox: Automated Discovery of Fine-Grained Performance Differences Between Language Models","created":"2025-06-02","cited_by_count":5,"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":"2505.16077","title":"Ensembling Sparse Autoencoders","created":"2025-05-21","cited_by_count":3,"area":"mechinterp"},{"id":"2509.03738","title":"Mechanistic Interpretability with Sparse Autoencoder Neural Operators","created":"2025-09-03","cited_by_count":3,"area":"mechinterp"},{"id":"2511.16309","title":"Sparse Autoencoders are Topic Models","created":"2025-11-20","cited_by_count":3,"area":null},{"id":"2512.07355","title":"A Geometric Unification of Concept Learning with Concept Cones","created":"2025-12-08","cited_by_count":3,"area":"mechinterp"},{"id":"2504.10833","title":"Measuring the (Un)Faithfulness of Concept-Based Explanations","created":"2025-04-15","cited_by_count":2,"area":null},{"id":"2506.01247","title":"Beyond Interpretability: When, Why, and How Sparse Autoencoders Enable Label-Free Visual Steering","created":"2025-06-02","cited_by_count":2,"area":"mechinterp"},{"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":"2601.20028","title":"Decomposing multimodal embedding spaces with group-sparse autoencoders","created":"2026-01-27","cited_by_count":2,"area":"mechinterp"},{"id":"2604.14925","title":"Improving Sparse Autoencoder with Dynamic Attention","created":"2026-04-16","cited_by_count":2,"area":"mechinterp"},{"id":"2605.13675","title":"Characterizing Universal Object Representations Across Vision Models","created":"2026-05-13","cited_by_count":2,"area":null},{"id":"2605.31245","title":"Toward Identifiable Sparse Autoencoders","created":"2026-05-29","cited_by_count":2,"area":"mechinterp"},{"id":"2606.24716","title":"Evaluating the Interpretability of Sparse Autoencoders with Concept Annotations","created":"2026-06-23","cited_by_count":2,"area":"mllm"},{"id":"2507.05810","title":"Concept-Based Mechanistic Interpretability Using Structured Knowledge Graphs","created":"2025-07-08","cited_by_count":1,"area":"mechinterp"},{"id":"2509.24793","title":"Sparse Autoencoders Make Audio Foundation Models more Explainable","created":"2025-09-29","cited_by_count":1,"area":"mechinterp"},{"id":"2510.25512","title":"FaCT: Faithful Concept Traces for Explaining Neural Network Decisions","created":"2025-10-29","cited_by_count":1,"area":null},{"id":"2512.02194","title":"Enforcing Orderedness to Improve Feature Consistency","created":"2025-12-01","cited_by_count":1,"area":"mechinterp"},{"id":"2512.09730","title":"Interpreto: An Explainability Library for Transformers","created":"2025-12-10","cited_by_count":1,"area":null},{"id":"2512.18930","title":"LouvreSAE: Sparse Autoencoders for Interpretable and Controllable Style Transfer","created":"2025-12-22","cited_by_count":1,"area":"mechinterp"},{"id":"2602.22600","title":"Transformers converge to invariant algorithmic cores","created":"2026-02-26","cited_by_count":1,"area":null},{"id":"2603.07335","title":"VisualScratchpad: Inference-time Visual Concepts Analysis in Vision Language Models","created":"2026-03-07","cited_by_count":1,"area":"mllm"},{"id":"2603.13884","title":"SCoCCA: Multi-modal Sparse Concept Decomposition via Canonical Correlation Analysis","created":"2026-03-14","cited_by_count":1,"area":"lr"},{"id":"2605.00474","title":"From Local to Global to Mechanistic: An iERF-Centered Unified Framework for Interpreting Vision Models","created":"2026-05-01","cited_by_count":1,"area":"mechinterp"},{"id":"2605.12809","title":"Correcting Influence: Unboxing LLM Outputs with Orthogonal Latent Spaces","created":"2026-05-12","cited_by_count":1,"area":null},{"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":"2606.09653","title":"A Unifying Framework for Concept-Based Representational Similarity","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2606.12138","title":"Unstable Features, Reproducible Subspaces: Understanding Seed Dependence in Sparse Autoencoders","created":"2026-06-10","cited_by_count":1,"area":"mechinterp"},{"id":"2606.14758","title":"Disentangling Hallucinations: Orthogonal Semantic Projection for Robust Interpretability","created":"2026-06-08","cited_by_count":1,"area":"mllm"},{"id":"2607.08605","title":"When Structured Sparse Autoencoders Learn Consistent Concepts Across Modalities","created":"2026-07-09","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":"2505.23917","title":"Representational Difference Explanations","created":"2025-05-29","cited_by_count":0,"area":null},{"id":"2510.20762","title":"MEIcoder: Decoding Visual Stimuli from Neural Activity by Leveraging Most Exciting Inputs","created":"2025-10-23","cited_by_count":0,"area":null},{"id":"2511.09432","title":"Equivariant Sparse Autoencoders: Mechanistic Interpretability of Neural Networks on Symmetric Data","created":"2025-11-12","cited_by_count":0,"area":"mechinterp"},{"id":"2512.11263","title":"Features Emerge as Discrete States: The First Application of SAEs to 3D Representations","created":"2025-12-12","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":"2602.10168","title":"EVA: Towards a universal model of the immune system","created":"2026-02-10","cited_by_count":0,"area":null},{"id":"2603.07402","title":"Generalizing Linear Autoencoder Recommenders with Decoupled Expected Quadratic Loss","created":"2026-03-08","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":"2604.13304","title":"Can Cross-Layer Transcoders Replace Vision Transformer Activations? An Interpretable Perspective on Vision","created":"2026-04-14","cited_by_count":0,"area":"mechinterp"},{"id":"2605.11203","title":"How Far Does a Shared Linear Map Go? Probing Feature-Space Manipulability for Image Editing","created":"2026-05-11","cited_by_count":0,"area":null},{"id":"2605.20337","title":"Capability $\\neq$ Interpretability: Human Interpretability of Vision Foundation Models","created":"2026-05-19","cited_by_count":0,"area":null},{"id":"2605.31304","title":"Interpretability Without Tradeoffs: Disentangling Polysemanticity At Equal Predictive Performance","created":"2026-05-29","cited_by_count":0,"area":null},{"id":"2606.02385","title":"How Optimality Structures Sparse Dictionaries: Theory for Interpreting SAE Representations","created":"2026-06-01","cited_by_count":0,"area":"mechinterp"},{"id":"2606.13934","title":"Adversarial Concept Search: Predicting Compositional Errors From Feature Geometry","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.06328","title":"Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models","created":"2026-07-07","cited_by_count":0,"area":"driving"},{"id":"2607.28386","title":"Explaining Image Similarity with Automatically Extracted Concept Activation Vectors","created":"2026-07-30","cited_by_count":0,"area":null},{"id":"2608.16669","title":"Concept-based explanation of gene expression prediction from H&E images","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2608.20117","title":"SAE-Xplainers: Rule-Based Feature Interpretation for Extreme Earth Events","created":"2026-08-20","cited_by_count":0,"area":"mechinterp"},{"id":"2608.26136","title":"Reward-Informed Sparse Autoencoders and the Solution-Completeness Confound","created":"2026-06-25","cited_by_count":0,"area":"mechinterp"},{"id":"2608.27515","title":"A Deeper Analysis of Block-Sparse Featurizers","created":"2026-08-27","cited_by_count":0,"area":"mechinterp"},{"id":"2609.13198","title":"SPICE: Simple Polysemantic Feature Interpretation via Clustering-based Explanation","created":"2026-08-14","cited_by_count":0,"area":null},{"id":"2609.29551","title":"HiPACE: Hierarchical Phase-Boundary Analysis and Controlled Evaluation of Feature Absorption in Sparse Autoencoders","created":"2026-08-26","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":"2610.03698","title":"Decoding the Functional Roles of Register and High-Norm Patch Tokens in Vision Transformers","created":"2026-10-02","cited_by_count":0,"area":"mechinterp"},{"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":"2610.04112","title":"The Independence Prior of SAEs Fragments Visual Concepts","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":"2610.13992","title":"How Vision Transformers Represent Position: A Mechanistic Comparison of Absolute and Rotary Positional Encodings","created":"2026-09-26","cited_by_count":0,"area":null}],"next_cursor":null}