INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

atcher

-0.28

æŁĵ

-0.26

UIL

-0.25

nesia

-0.25

ä¸Ģå¹ķ

-0.24

FromClass

-0.24

äººæ°ĳæ³ķéĻ¢

-0.24

è¨¾

-0.24

Gul

-0.24

 europe

-0.23

POSITIVE LOGITS

å¤ĸåĽ½è¯Ń

0.28

ç±į

0.27

hop

0.26

Ø®Ø´

0.25

çº§

0.25

 vÆ°á»£t

0.25

æ°Ĺ

0.25

ktop

0.25

éĶĢ

0.25

hone

0.24

Activations Density 0.009%

No Known Activations

This feature has no known activations.