© 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 · 15-RESID-POST-AA · 121414 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
121414

INDEX

Explanations

of

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

 Secondly

-0.07

 addChild

-0.07

getView

-0.07

imb

-0.07

év

-0.06

琪

-0.06

.Msg

-0.06

unga

-0.06

 DEAL

-0.06

TexImage

-0.06

POSITIVE LOGITS

장을

0.07

/')↵

0.07

점을

0.07

gtk

0.07

']=

0.07

 обществ

0.07

 ">↵

0.07

鲁迅

0.07

styled

0.07

=wx

0.07

Activations Density 0.016%

No Known Activations