© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 29411 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
29411

INDEX

Explanations

ellipses

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

xBF

-0.07

activo

-0.07

PM

-0.07

ADIO

-0.07

 receipt

-0.07

TestCategory

-0.07

 collar

-0.07

lash

-0.07

IDA

-0.07

TO

-0.07

POSITIVE LOGITS

dü

0.09

getLocation

0.08

dot

0.07

ขน

0.07

mü

0.07

含义

0.07

gy

0.07

Hut

0.07

 granite

0.06

绒

0.06

Activations Density 0.019%

No Known Activations