Transformer-based architectures have become the shared backbone of natural language processing and computer vision. However, understanding how these models operate remains challenging, particularly in vision settings, where images are processed as sequences of patch tokens. Existing interpretability tools often focus on isolated components or expert-oriented analysis, leaving a gap in guided, end-to-end understanding of the full inference pipeline. To bridge this gap, we present ViT-Explainer, a web-based interactive system that provides an integrated visualization of Vision Transformer inference, from patch tokenization to final classification. The system combines animated walkthroughs, patch-level attention overlays, and a vision-adapted Logit Lens within both guided and free exploration modes. A user study with six participants suggests that ViT-Explainer is easy to learn and use, helping users interpret and understand Vision Transformer behavior.

翻译：基于Transformer的架构已成为自然语言处理与计算机视觉领域的共享主干。然而，理解这些模型的工作机制仍具挑战性——尤其在视觉任务中，图像需被处理为补丁令牌序列。现有可解释性工具往往聚焦于孤立组件或面向专家的分析，缺乏对完整推理流程的引导式端到端理解。为弥合这一缺口，我们提出ViT-Explainer——一个基于网页的交互式系统，可提供从补丁令牌化到最终分类的视觉Transformer推理全流程集成可视化。该系统在引导式与自由探索模式下，综合运用动画导览、补丁级注意力覆盖层以及适配视觉领域的Logit Lens工具。一项涉及六名参与者的用户研究表明，ViT-Explainer易于学习与使用，能够帮助用户解读并理解视觉Transformer的行为机制。