Watch a Language Model Think
TokenPrint traces transformer inference as it happens. Follow tokens, tensors, attention, KV cache and generation through a real model.
TokenPrint
Built for the moments that matter most.
01 — Real Model Execution
See what the model actually computes.
Trace real transformer execution from input tokens through embeddings, normalization, attention, MLPs, residual streams and logits.
02 — Every Tensor, Inspectable
Follow representations at every stage.
Inspect tensor shapes, parameters, hidden states, attention weights and model metadata directly inside the computation.
03 — Token-by-Token Generation
Watch generation unfold.
Follow a token through the transformer during prefill and decode, with KV-cache state and operation progress visible as inference runs.
04 — Attention, Decoded
See how tokens interact.
Explore Q, K and V projections, grouped-query attention, RoPE, attention scores and weighted values as the computation happens.
See how a model thinks.
Follow the structures, tensors, and computations behind every prediction.
Understand the architecture
Inspect layers, tensors, residual streams, and model topology.
See attention unfold
Follow Q, K, V, attention scores, RoPE, and weighted values.
Watch generation happen
Trace prefill, KV cache, decoding, logits, and next-token prediction.