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

rated

-0.31

ä¾Ľ

-0.26

uable

-0.26

çİĩè¾¾åĪ°

-0.25

straction

-0.25

ives

-0.25

ableView

-0.24

ãģ¾ãģĽãĤĵ

-0.24

ey

-0.24

 independence

-0.24

POSITIVE LOGITS

æĺ¯ä¸ŃåĽ½

0.30

å¹³

0.27

åĩĮæĻ¨

0.24

å§ĵ

0.24

ped

0.24

mug

0.23

æĺ¯è¦ģ

0.23

ç»ĻåŃ©åŃĲ

0.23

é«ĺåº¦

0.23

:host

0.22

Activations Density 0.002%

No Known Activations

This feature has no known activations.