© 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 · 11975 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
11975

INDEX

Explanations

Gre

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

%[

-0.08

-0.08

ower

-0.08

(Matrix

-0.07

 eased

-0.07

_Run

-0.07

 tolerate

-0.07

知

-0.07

鄣

-0.07

 Gong

-0.07

POSITIVE LOGITS

交通大学

0.08

 xmlhttp

0.08

 Newton

0.08

-heavy

0.08

IMPORTANT

0.07

Requirements

0.07

 Joomla

0.07

 uniqu

0.07

 hükü

0.07

 siguiente

0.07

Activations Density 0.009%

No Known Activations