Entroπa ← Playground

Weights Visualizer

Model Params Tensors Experts

Architecture

parameters per layer · in forward order
attention experts / MoE embed / head norm / other

Weight matrix

< 00> 0

Value distribution

Token routing & expert flow

simulated forward pass
Each token is routed to its top-k experts by a softmax gate; the fill inside each expert shows its cumulative load. Cold experts are the pruning candidates — carry the same model into the Experts Pruner.

Drop weights to load

.safetensors, or a torch .pt / .pth · nothing leaves your machine