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

 bart

-0.28

åĪļå¥½

-0.28

 getResult

-0.25

æ¥¹

-0.25

ä¸§å¤±

-0.25

 disciplined

-0.25

çĿĢä»ĸ

-0.25

éĹ®ä»ĸ

-0.24

å¤Ł

-0.24

åıĳæĺİä¸ĵåĪ©

-0.24

POSITIVE LOGITS

Ð¾Ð¼Ð½

0.29

 segregated

0.28

osh

0.26

oling

0.25

éĨĴ

0.25

olls

0.25

atch

0.24

éĵ²

0.24

.Handler

0.24

aroo

0.24

Activations Density 0.007%

No Known Activations

This feature has no known activations.