© 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 · 24616 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
11-RESID-POST-AA
24616

INDEX

Explanations

=

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

_MATRIX

-0.07

respuesta

-0.07

▩

-0.07

>",

-0.07

Ő

-0.07

毹

-0.06

 תש

-0.06

 możemy

-0.06

פתר

-0.06

POSITIVE LOGITS

TEXT

0.07

忘了

0.07

Trade

0.07

 Words

0.07

换来

0.07

 maintain

0.07

 pertaining

0.07

LOGY

0.07

まり

0.07

/M

0.07

Activations Density 0.004%

No Known Activations