© 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 · 44651 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
44651

INDEX

Explanations

Code

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

 Hulu

-0.07

 TextEditingController

-0.07

TextView

-0.07

 Drinking

-0.07

.render

-0.07

 Cutter

-0.07

 baptism

-0.07

raphic

-0.07

 Hunger

-0.07

enever

-0.07

POSITIVE LOGITS

辿

0.07

_ANT

0.07

 colle

0.07

ㅐ

0.07

_pct

0.07

对方

0.07

нул

0.07

 공간

0.06

Fair

0.06

 paired

0.06

Activations Density 0.060%

No Known Activations