qwen3.6-27b-mlp-jlens

Model Card

The workspace Jacobian lens (Jacobian Lens paper; lenses from camilablank/workspace-lenses) is the averaged Jacobian Econtext[∂hpenult / ∂hℓ] of the penultimate residual (last block omitted) w.r.t. the layer-ℓ residual, read out with the model's finalnorm + WU. This repo composes J[42] with layer-42's MLP weights to give the averaged Jacobian to/from the MLP — i.e. the MLP state read through the workspace lens. d = 5120, dff = 17408, model = Qwen/Qwen3.6-27B, penultimate block = 62. - The read-out is an exact averaged Jacobian: it reads the current-token concept/operation the MLP contributes (e.g. bug → removing, antibiotics → healing, capital → geographical). It is a concept readout, not a…

Excerpt from the card by De Schamphelaere, licensed other.

Identity and Version

Repository

ceselder/qwen3.6-27b-mlp-jlens

Publisher

De Schamphelaere

Task

Not stated by the source

Modality

Other

Library

Not stated by the source

Parameters

Not stated by the source

Languages

Not stated by the source

Revision

30f19fa2bfc92cc024aadb9470ae8b0fe72a8639

First published

2026-09-19

Last updated

2026-09-20

Files and Weights

71 files, 18.4 GB in total. The weights are 65 files totalling 18.4 GB in safetensors.

License and Download

License

other

Access

Open weights, no gate

Download size

18.4 GB

Built From

• Derived from Qwen/Qwen3.6-27B

Memory Requirements

Weights only, from the published parameter count; the key-value cache and runtime add to this.