© 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 · 45900 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
45900

INDEX

Explanations

file operations

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

typeName

-0.07

 mnie

-0.07

 wśród

-0.07

Beyond

-0.06

icha

-0.06

YouTube

-0.06

Liter

-0.06

eyond

-0.06

 loung

-0.06

ugins

-0.06

POSITIVE LOGITS

_heat

0.08

腳

0.07

.accessToken

0.07

셤

0.07

EGL

0.07

東西

0.07

束

0.07

斝

0.07

_activation

0.07

`;↵↵

0.07

Activations Density 0.018%

No Known Activations