© 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 · 7-RESID-POST-AA · 102760 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
102760

INDEX

Explanations

Cyrillic

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

 socket

-0.07

arging

-0.07

ognition

-0.07

 SignIn

-0.07

 stools

-0.07

 disple

-0.07

aer

-0.07

 solic

-0.07

 comedic

-0.07

 сраз

-0.07

POSITIVE LOGITS

<Self

0.07

Há

0.06

 occasional

0.06

 Wimbledon

0.06

.MODEL

0.06

東西

0.06

繁

0.06

Ive

0.06

אנחנו

0.06

_INTERFACE

0.06

Activations Density 0.003%

No Known Activations