© Neuronpedia 2026

Privacy & Terms Blog GitHub Slack Twitter Contact

Neuronpedia

Natural Language

NEW Assistant AxisNEW Circuit TracerUPDATESteer SAE Evals ExportsAPI Community Blog Privacy & Terms Contact

QWEN2.5-7B-IT · 11-RESID-POST-AA · 65287 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
65287

INDEX

Explanations

Warnings and disclaimers

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

_colour

-0.07

₹

-0.07

皴

-0.06

OPT

-0.06

Colour

-0.06

curl

-0.06

 UIAlert

-0.06

 curvature

-0.06

 Bands

-0.06

○

-0.06

POSITIVE LOGITS

 excuses

0.08

سكو

0.08

 vidéo

0.07

تضمن

0.07

 Millennials

0.07

ᴖ

0.07

喾

0.07

🚘

0.07

 kısa

0.07

ﺹ

0.07

Activations Density 0.021%

No Known Activations