This repository contains a BatchTopK sparse autoencoder (SAE) trained on the raw residual-stream output of Qwen/Qwen3-32B at model.layers[36] (zero-based, after the 37th transformer block and before the final norm). The checkpoint was trained against Qwen3-32B revision 9216db5781bf21249d130ec9da846c4624c16137. It has 131,072 features, input dimension 5,120, and target average sparsity k=64. - encoder.safetensors: encoder weight and bias. - decoder.safetensors: decoder weight, decoder bias, serving threshold, and k. - loader.py: standalone PyTorch loader with encode and decode methods. - saeconfig.json: model coordinate, architecture, training, and data metadata. - trainingdatamanifest.json…
Independent publisher
Kemalau
AAIREPE
AI for Education/ computational cognition science
Models in Library1
Datasets in Library0
Models on Hugging Face1
Followers—
Compare the published evidence
This profile connects the 1 model and dataset record shown below to their upstream cards and sources. The library counts describe SAVRN's coverage, rather than this publisher's entire output.
Reported licenses: apache-2.0. Open a record to review its specific license and conditions.
Compare model specifications, source dates, and hardware estimates on the individual records. Publisher identity verification is separate from a model's quality, deployment readiness, or suitability for your work.