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

æĸ¹åľĨ

-0.26

çļĦå¥³äºº

-0.26

deen

-0.25

è¿ĩåİ»çļĦ

-0.25

æıĲåįĩ

-0.25

çļĦçĶ·äºº

-0.25

ä¸¤å¹´åīį

-0.25

OSH

-0.24

åĪĿæŃ¥

-0.24

 Glyph

-0.24

POSITIVE LOGITS

 tort

0.29

 rules

0.27

 espec

0.25

 cloud

0.25

 (...)

0.25

 catch

0.24

leur

0.24

(serv

0.24

 fres

0.24

sir

0.23

Activations Density 0.003%

No Known Activations

This feature has no known activations.