© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 15-RESID-POST-AA · 13596 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
13596

INDEX

Explanations

:

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

AMC

-0.07

ISS

-0.07

乡土

-0.07

statusCode

-0.07

 trustworthy

-0.07

 historical

-0.07

Police

-0.07

 Blanch

-0.07

隆

-0.06

麻醉

-0.06

POSITIVE LOGITS

 /////

0.07

واب

0.07

 Negot

0.07

'=>

0.07

ensely

0.06

.Cmd

0.06

씩

0.06

gow

0.06

しゃ

0.06

.Return

0.06

Activations Density 0.001%

No Known Activations