© 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 · 19-RESID-POST-AA · 70445 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
70445

INDEX

Explanations

file extraction code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

好运

-0.08

引

-0.07

終

-0.07

_reference

-0.07

未成年

-0.07

 baked

-0.07

 Alma

-0.07

 newObj

-0.07

烫

-0.07

 prakt

-0.07

POSITIVE LOGITS

 Pelosi

0.07

--

0.07

bem

0.07

дов

0.07

ioned

0.06

섵

0.06

亮相

0.06

,y

0.06

콩

0.06

魉

0.06

Activations Density 0.000%

No Known Activations