{"total":18,"rows":[{"id":"2308.14179","title":"Towards Vision-Language Mechanistic Interpretability: A Causal Tracing Tool for BLIP","created":"2023-08-27","cited_by_count":62,"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":"2601.21900","title":"TraceRouter: Robust Safety for Large Foundation Models via Path-Level Intervention","created":"2026-01-29","cited_by_count":11,"area":"mechinterp"},{"id":"2501.19066","title":"Concept Steerers: Leveraging K-Sparse Autoencoders for Test-Time Controllable Generations","created":"2025-01-31","cited_by_count":7,"area":"mechinterp"},{"id":"2603.11493","title":"OrthoEraser: Coupled-Neuron Orthogonal Projection for Concept Erasure","created":"2026-03-12","cited_by_count":7,"area":"mechinterp"},{"id":"2510.03186","title":"Superposition disentanglement of neural representations reveals hidden alignment","created":"2025-10-03","cited_by_count":4,"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":"2603.03163","title":"Conditioned Activation Transport for T2I Safety Steering","created":"2026-03-03","cited_by_count":3,"area":"mechinterp"},{"id":"2606.06664","title":"Inside the Visual Mind: Neuroscience-Motivated Concept Circuits for Interpreting and Steering Vision Transformers","created":"2026-06-04","cited_by_count":3,"area":"mechinterp"},{"id":"2606.08454","title":"Beyond Linear Activation Steering: Invertible Latent Transformations for Controlling LLM Behavior","created":"2026-06-07","cited_by_count":3,"area":"mechinterp"},{"id":"2601.20028","title":"Decomposing multimodal embedding spaces with group-sparse autoencoders","created":"2026-01-27","cited_by_count":2,"area":"mechinterp"},{"id":"2411.12589","title":"ULTra: Unveiling Latent Token Interpretability in Transformer-Based Understanding and Segmentation","created":"2024-11-15","cited_by_count":1,"area":"mechinterp"},{"id":"2507.18512","title":"Explaining How Visual, Textual and Multimodal Encoders Share Concepts","created":"2025-07-24","cited_by_count":1,"area":"mechinterp"},{"id":"2509.14846","title":"[Re] Improving Interpretation Faithfulness for Vision Transformers","created":"2025-09-18","cited_by_count":1,"area":"mechinterp"},{"id":"2602.07311","title":"LUCID-SAE: Learning Unified Vision-Language Sparse Codes for Interpretable Concept Discovery","created":"2026-02-07","cited_by_count":1,"area":"mechinterp"},{"id":"2609.05575","title":"Capsule Lens: Locating and Tracking Concept Geometry in Model Representations","created":"2026-09-04","cited_by_count":1,"area":"mechinterp"},{"id":"2506.20083","title":"Bridging Compositional and Distributional Semantics: A Survey on Latent Semantic Geometry via AutoEncoder","created":"2025-06-25","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"}],"next_cursor":null}