© 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 · 15-RESID-POST-AA · 43172 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
43172

INDEX

Explanations

graph

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

 eyewitness

-0.08

 thigh

-0.07

(person

-0.07

葶

-0.07

wand

-0.07

 OPTION

-0.07

 questionnaire

-0.07

 stylist

-0.07

 intervening

-0.07

 HISTORY

-0.07

POSITIVE LOGITS

basis

0.07

 Broadway

0.07

encil

0.07

ﺫ

0.07

任意

0.07

.bucket

0.07

{↵

0.06

?(

0.06

遵

0.06

："

0.06

Activations Density 0.006%

No Known Activations