© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Jacobian LensNEW

Natural Language

MAY 26 Assistant AxisJAN 26 Circuit TracerAPR 26Steer SAE Evals Exports interp-engineNEW Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 19-RESID-POST-AA · 72202 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
72202

INDEX

Explanations

TO

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Architecture

standard

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

Show PlotsShow ExplanationShow ActivationsShow Test FieldShow SteerShow Link

IFrame

Link

Negative Logits

 Goat

-0.07

 polished

-0.07

氘

-0.07

chief

-0.06

<Image

-0.06

Miy

-0.06

 libertine

-0.06

.Movie

-0.06

 Discipline

-0.06

 renal

-0.06

POSITIVE LOGITS

 AUTH

0.07

 overweight

0.07

ederal

0.07

课

0.07

_reply

0.07

开来

0.06

上传

0.06

⾏

0.06

erequisite

0.06

思い出

0.06

Activations Density 0.001%

No Known Activations