© 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 · 69332 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
69332

INDEX

Explanations

omer

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

 Congo

-0.08

ud

-0.08

"No

-0.07

ENV

-0.07

 معدل

-0.07

rex

-0.07

 Ecuador

-0.07

 valor

-0.07

信用

-0.07

"A

-0.06

POSITIVE LOGITS

 Coca

0.07

omed

0.07

漶

0.07

owied

0.07

.EntityFramework

0.07

 permanent

0.06

..

0.06

">${

0.06

 Homepage

0.06

Gam

0.06

Activations Density 0.001%

No Known Activations