© 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 · 11-RESID-POST-AA · 1121 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
1121

INDEX

Explanations

name

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

 Gordon

-0.07

getPosition

-0.07

핛

-0.07

すれば

-0.07

뿍

-0.07

combat

-0.07

施展

-0.06

GRP

-0.06

셑

-0.06

⏫

-0.06

POSITIVE LOGITS

.uml

0.07

有趣

0.07

*scale

0.07

umu

0.07

 typeof

0.07

 מכ

0.06

use

0.06

)*

0.06

 이미

0.06

-*

0.06

Activations Density 0.001%

No Known Activations