In-browser X-ray for neural networks: run ONNX models on WebGPU and watch activations, ablate attention heads, and diff checkpoints. No server, no install.
A comprehensive tool for visualizing and analyzing model execution, offering interactive graphs, memory plots, tensor details, buffer overviews, operation flow graphs, and multi-instance support with file or SSH-based report loading.
Capture every activation and gradient of any PyTorch model — forward and backward — with automatic graph visualization, rich metadata, and live interventions. Works on any architecture, including dynamic and recurrent ones.