Compare Architecture Across Qwen, Llama, Gemma, Mistral, Gpt-2

TokenPrint renders a real LLM forward pass in interactive 3D: attention heads, RoPE, GQA and the residual stream traced from actual tensors or a local GGUF file. Four modes (architecture, generation, walkthrough, debugger) with provenance tagging. Runs a FastAPI backend plus a Next.js/Three.js frontend.

AI Tools | TypeScript · transformer-visualization · llm-interpretability