© 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 · 19-RESID-POST-AA · 90030 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
19-RESID-POST-AA
90030

INDEX

Explanations

Comparing age

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

islation

-0.07

这一次

-0.07

(Guid

-0.07

烟草

-0.07

ULE

-0.07

Luo

-0.07

/documentation

-0.06

UGC

-0.06

חר

-0.06

tok

-0.06

POSITIVE LOGITS

⁾

0.08

🐯

0.08

녤

0.08

 BigDecimal

0.07

mag

0.07

_intent

0.07

�

0.07

0.07

主宰

0.07

 отлично

0.07

Activations Density 0.029%

No Known Activations