© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

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

QWEN2.5-7B-IT · 15-RESID-POST-AA · 15943 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
15943

INDEX

Explanations

when

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

煮

-0.07

 spend

-0.07

(SE

-0.07

Burn

-0.07

 chụp

-0.07

(ind

-0.07

();

-0.07

-0.07

Hun

-0.07

Yam

-0.07

POSITIVE LOGITS

director

0.08

nearest

0.07

王者

0.07

 Doctors

0.07

偓

0.07

 pleas

0.07

_session

0.07

_dbg

0.07

诰

0.07

 grabs

0.07

Activations Density 0.072%

No Known Activations