© 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 · 7-RESID-POST-AA · 38305 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
38305

INDEX

Explanations

0

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

россий

-0.08

loader

-0.07

leted

-0.07

Leaks

-0.07

 implicated

-0.07

 cheats

-0.07

edx

-0.07

 skating

-0.07

mPid

-0.07

eming

-0.07

POSITIVE LOGITS

 Thurs

0.07

تن

0.07

טוב

0.07

_REFRESH

0.07

ур

0.06

TableWidgetItem

0.06

珫

0.06

榉

0.06

ن

0.06

cư

0.06

Activations Density 0.001%

No Known Activations