{"total":22,"rows":[{"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":"2602.02315","title":"The Shape of Beliefs: Geometry, Dynamics, and Interventions along Representation Manifolds of Language Models' Posteriors","created":"2026-02-02","cited_by_count":15,"area":null},{"id":"2605.01148","title":"Arithmetic in the Wild: Llama uses Base-10 Addition to Reason About Cyclic Concepts","created":"2026-05-01","cited_by_count":10,"area":null},{"id":"2606.25234","title":"Structuring Sparsity: Block-Sparse Featurizers Capture Visual Concept Manifolds","created":"2026-06-23","cited_by_count":5,"area":null},{"id":"2606.12360","title":"Anatomy of Post-Training: Using Interpretability to Characterize Data and Shape the Learning Signal","created":"2026-06-10","cited_by_count":2,"area":null},{"id":"2606.23443","title":"What Does a Chemical Language Model Know About Molecules?","created":"2026-06-22","cited_by_count":2,"area":null},{"id":"2607.01987","title":"Understanding Geometric Representations in Self-Supervised Vision Transformers via Subspace Intervention","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2603.16840","title":"What DINO saw: ALiBi positional encoding reduces positional bias in Vision Transformers","created":"2026-03-17","cited_by_count":1,"area":null},{"id":"2605.28870","title":"Representation Alignment Rests on Linear Structure","created":"2026-05-22","cited_by_count":1,"area":null},{"id":"2606.09653","title":"A Unifying Framework for Concept-Based Representational Similarity","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2604.05296","title":"From Measurement to Mitigation: Quantifying and Reducing Identity Leakage in Image Representation Encoders with Linear Subspace Removal","created":"2026-04-07","cited_by_count":0,"area":null},{"id":"2604.14433","title":"Zero-Ablation Overstates Register Content Dependence in DINO Vision Transformers","created":"2026-04-15","cited_by_count":0,"area":null},{"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":"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":"2609.01551","title":"What, Where, and How: Probing Spatiotemporal Representations in Video Foundation Models","created":"2026-09-01","cited_by_count":0,"area":null},{"id":"2609.05399","title":"From Interpretability Methods to Interpretable Models","created":"2026-09-04","cited_by_count":0,"area":null},{"id":"2609.13072","title":"MAxBench: A Multinomial Concept Recovery Benchmark","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2609.32619","title":"Intuition vectors","created":"2026-09-26","cited_by_count":0,"area":null},{"id":"2609.35351","title":"Interference Beyond Geometry in Concept Extraction","created":"2026-09-28","cited_by_count":0,"area":null},{"id":"2610.12004","title":"The Polytopal Neural Network","created":"2026-10-08","cited_by_count":0,"area":null},{"id":"2610.13299","title":"Decoding Register Tokens Preserves Global Scene Details","created":"2026-10-09","cited_by_count":0,"area":null}],"next_cursor":null}