© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 4253 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
4253

INDEX

Explanations

En

np_max-act · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 sistem

-0.07

-0.06

谎言

-0.06

是

-0.06

 Higher

-0.06

 simplement

-0.06

updating

-0.06

 Adams

-0.06

/ws

-0.06

=val

-0.06

POSITIVE LOGITS

xt

0.07

vron

0.07

.async

0.07

 DCHECK

0.07

ynamics

0.07

Getty

0.07

 Huffington

0.07

饨

0.07

anggan

0.07

暮ら

0.06

Activations Density 0.050%

No Known Activations