cs.ROOct 30, 2026

Mechanistic Interpretability for End-to-End Self-Driving

Authors: Manav Gagvani, Benjamin Namikas, Sivamurugan Velmurugan, Nysa Kumar, Shrey Sharma, Thomas Peterson, Pratyush Mathur, Hyunseo Chang, 

Organizations: Department of Electrical & Computer Engineering, Purdue University · Department of Computer Science, Purdue University

Abstract

End-to-end (E2E) autonomous driving models achieve strong planning performance but remain largely opaque, limiting observability and trust. We apply mechanistic interpretability to E2E driving by training Sparse Autoencoders (SAEs) on the internal activations of a simple, single-camera end-to-end path planning model. Unsupervised clustering of SAE latents reveals interpretable structure aligned with route intent, vehicle speed, and braking behavior, recovering route intent with 98.3% accuracy without supervision. Through paired counterfactual image edits, we further show that specific SAE features are visually grounded and systematically respond to scene changes such as traffic light state and stop sign presence. Steering individual SAE latents produces predictable, monotonic changes in planner outputs including lateral displacement, curvature, and braking. Finally, we demonstrate a practical application of these representations: we build a lightweight adapter trained on SAE latents that reduces trajectory selection error by 3.44%, outperforming an equivalent adapter that omits SAE latents, confirming that the sparse representation captures useful information for interpretability. Code and visualizations are available at https://mgagvani.github.io/mechanistic-interpretability-for-e2e-driving/

Figures & tables

Appendix figures & tables13 assets

Supplementary material from the paper’s appendix.

Appendix

Explore similar work

CardsList
  1. Driving the Wrong Way: Leveraging Interpretability in End2End Autonomous Driving Models

    Jul 7, 2026Franz Motzkus, Sebastian BernhardEnd-to-End Autonomous DrivingInterpretable ML

  2. PRISM: Privileged Probabilistic Latent Supervision for End-to-End Autonomous Driving Motion Planning

    Aug 2, 2026Volodymyr Havrylov, Faris Janjoš, Andreas Look +2End-to-End Autonomous DrivingAutonomous Driving Planning