© 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 · 15-RESID-POST-AA · 19837 ｜ Neuronpedia

Home
Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
Qwen2.5-7B-IT
Resid Post - 131k
15-RESID-POST-AA
19837

INDEX

Explanations

bert

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_15/trainer_1

Dataset (Dashboard)

Various

Features

131,072

Data Type

float32

Hook Name

blocks.15.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

柰

-0.08

ᑎ

-0.07

 때문이다

-0.07

神通

-0.07

🍊

-0.07

 hugely

-0.07

Mü

-0.07

![

-0.07

ssc

-0.07

勐

-0.06

POSITIVE LOGITS

hide

0.07

Atom

0.07

 visto

0.07

verified

0.07

 Cutting

0.06

Endpoint

0.06

 Sending

0.06

_false

0.06

套

0.06

-four

0.06

Activations Density 0.010%

No Known Activations