© 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 · 41112 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
7-RESID-POST-AA
41112

INDEX

Explanations

Artists, art

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

.scrollTop

-0.07

 slideshow

-0.07

磕

-0.07

 careless

-0.07

🧐

-0.07

 najwyższ

-0.07

𬤊

-0.07

=plt

-0.07

 statically

-0.07

ání

-0.07

POSITIVE LOGITS

book

0.07

近年

0.07

 harb

0.07

Ƒ

0.07

Mon

0.07

Mich

0.07

娓

0.07

长效机制

0.06

0.06

WAV

0.06

Activations Density 0.002%

No Known Activations