© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Jacobian LensNEW

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals Exports interp-engineNEWAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 70620 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
70620

INDEX

Explanations

pwd

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

 نحو

-0.08

 Freed

-0.07

 Marr

-0.07

Bor

-0.07

 Residential

-0.07

 workshop

-0.07

 Gems

-0.07

Exercise

-0.07

 jams

-0.07

setName

-0.07

POSITIVE LOGITS

 Athen

0.07

 Alice

0.07

八字

0.07

谁

0.06

_via

0.06

.fin

0.06

.fasterxml

0.06

مقاط

0.06

Kid

0.06

孀

0.06

Activations Density 0.002%

No Known Activations