© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

APIAssistant AxisNEW Circuit TracerNEW Steer SAE Evals Exports Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 75180 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
75180

INDEX

Explanations

cargo

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_11/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.11.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

 Nepal

-0.07

loss

-0.07

St

-0.07

SEA

-0.06

 theat

-0.06

Vis

-0.06

 paused

-0.06

 sunday

-0.06

-0.06

POSITIVE LOGITS

 cargo

0.10

 Cargo

0.09

Cargo

0.08

 payload

0.08

cargo

0.07

货运

0.07

惹

0.07

ในการ

0.07

 Cameras

0.07

 scientific

0.07

Activations Density 0.004%

No Known Activations