© 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 · 19-RESID-POST-AA · 8757 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
8757

INDEX

Explanations

,

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Top Features by Cosine Similarity

Configuration

andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.19.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

Tea

-0.06

缣

-0.06

𬞟

-0.06

edy

-0.06

 nucleus

-0.06

藟

-0.06

scious

-0.06

制成

-0.06

.eth

-0.06

 Compute

-0.06

POSITIVE LOGITS

하도록

0.08

(rd

0.08

0.08

())↵

0.07

 دور

0.07

 Ownership

0.07

-reported

0.07

 Context

0.07

':↵

0.07

il

0.07

Activations Density 0.023%

No Known Activations