© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 34374 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
34374

INDEX

Explanations

transmit

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

졵

-0.07

nou

-0.07

魈

-0.07

🧚

-0.07

..."

-0.07

"?

-0.07

垸

-0.07

layın

-0.07

acağız

-0.07

%).

-0.07

POSITIVE LOGITS

 ترك

0.07

 Führung

0.07

.digest

0.07

诊治

0.06

回报

0.06

uckets

0.06

_SEPARATOR

0.06

;s

0.06

щения

0.06

ในฐาน

0.06

Activations Density 0.002%

No Known Activations