© 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 · 109962 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
109962

INDEX

Explanations

that

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

_Admin

-0.07

SELL

-0.07

 realizado

-0.07

กรม

-0.06

تجار

-0.06

🎠

-0.06

ceiving

-0.06

 ActionListener

-0.06

�

-0.06

 Hungarian

-0.06

POSITIVE LOGITS

DAC

0.07

 neurons

0.07

عا

0.07

ල

0.07

.max

0.07

Transfer

0.07

taient

0.07

 Scotland

0.07

fly

0.07

yntaxException

0.07

Activations Density 0.054%

No Known Activations