© 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 · 111930 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
111930

INDEX

Explanations

{

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

鲍

-0.08

pz

-0.07

 כג

-0.07

_CRC

-0.07

 taxonomy

-0.06

校

-0.06

mPid

-0.06

gid

-0.06

 повы

-0.06

 disclosures

-0.06

POSITIVE LOGITS

`()

0.07

𝕋

0.07

	Logger

0.07

iving

0.07

values

0.07

)};↵

0.07

 Champagne

0.07

Dar

0.07

ירה

0.07

ificado

0.07

Activations Density 0.001%

No Known Activations