© 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 · 77154 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
77154

INDEX

Explanations

country names

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

 Kart

-0.07

Such

-0.07

빻

-0.07

 Kumar

-0.07

arsimp

-0.07

🚕

-0.07

 nieruch

-0.07

 legitim

-0.07

𫫇

-0.07

 shit

-0.07

POSITIVE LOGITS

 catch

0.08

 serialized

0.07

catch

0.07

总

0.07

隨

0.07

-insert

0.07

.cljs

0.07

	catch

0.06

守

0.06

背上

0.06

Activations Density 0.031%

No Known Activations