© 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 · 7-RESID-POST-AA · 37569 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
37569

INDEX

Explanations

also

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_7/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.7.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

♾

-0.07

front

-0.07

ICIENT

-0.07

 endorsed

-0.06

>Contact

-0.06

-den

-0.06

-low

-0.06

.TR

-0.06

ptrdiff

-0.06

𝐅

-0.06

POSITIVE LOGITS

 Gaul

0.07

 cmake

0.07

既要

0.07

ออกไป

0.07

+xml

0.07

Maker

0.07

改革

0.07

并与

0.07

 fetal

0.07

分化

0.07

Activations Density 0.004%

No Known Activations