© 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 · 37994 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
37994

INDEX

Explanations

code files

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

ߡ

-0.08

뻑

-0.08

red

-0.07

뿟

-0.07

鞑

-0.07

LCD

-0.07

펨

-0.07

펶

-0.07

𫘪

-0.07

ilmington

-0.07

POSITIVE LOGITS

shift

0.07

ᵤ

0.07

 Depth

0.07

Frequency

0.07

$values

0.07

的地位

0.07

 innovations

0.07

Lo

0.07

➢

0.07

operations

0.07

Activations Density 0.002%

No Known Activations