© 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 · 19-RESID-POST-AA · 7508 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
7508

INDEX

Explanations

FONT

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

-framework

-0.08

 tenga

-0.08

-tag

-0.07

 araç

-0.07

 Garn

-0.07

垕

-0.07

 valueForKey

-0.07

conda

-0.07

 FetchType

-0.07

…but

-0.07

POSITIVE LOGITS

싀

0.07

	stop

0.07

म

0.07

調查

0.06

מעניק

0.06

_expect

0.06

 breakout

0.06

 combos

0.06

យ

0.06

 Cent

0.06

Activations Density 0.000%

No Known Activations