© 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 · 15-RESID-POST-AA · 118122 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
118122

INDEX

Explanations

flood

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

-paper

-0.07

manufact

-0.07

𬶮

-0.06

휑

-0.06

span

-0.06

#@

-0.06

 china

-0.06

Tuesday

-0.06

>@

-0.06

Math

-0.06

POSITIVE LOGITS

 Flood

0.09

 flood

0.09

.hxx

0.08

 uterus

0.07

_DECLS

0.07

 Conduct

0.07

_continuous

0.07

 floods

0.07

 würde

0.07

 migrating

0.07

Activations Density 0.003%

No Known Activations