端到端（E2E）自动驾驶模型虽具备较强的规划性能，但其内部机制仍 largely opaque，限制了系统的可观测性与可信度。本研究将机制可解释性应用于 E2E 驾驶场景，通过在简单的单摄像头端到端路径规划模型的内部激活值上训练稀疏自编码器（SAEs）来实现。对 SAE 潜在变量进行无监督聚类，揭示了与路线意图、车辆速度及制动行为相一致的可解释结构，并在无监督条件下以 98.3% 的准确率恢复路线意图。通过成对的反事实图像编辑，进一步证明特定 SAE 特征具有视觉接地性，并能系统性地响应交通灯状态和停车标志存在等场景变化。操控单个 SAE 潜在变量可使规划器输出产生可预测且单调的变化，包括横向位移、曲率和制动。最后，展示了这些表征的实际应用：构建了一个基于 SAE 潜在变量训练的轻量级适配器，使轨迹选择误差降低了 3.44%，优于省略 SAE 潜在变量的等效适配器，证实了稀疏表征捕获了对可解释性有用的信息。代码和可视化结果可在 https://mgagvani.github.io/mechanistic-interpretability-for-e2e-driving/ 获取。

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/