INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

ç³ľ

-0.26

 Polit

-0.24

 intel

-0.24

 Down

-0.24

tableFuture

-0.23

éĹ¨æ§Ľ

-0.23

ismic

-0.23

ampa

-0.23

âĿ

-0.23

agged

-0.23

POSITIVE LOGITS

<!--↵

0.28

yre

0.28

åĬ

0.25

.effects

0.25

nez

0.25

efe

0.23

ewire

0.23

)-(

0.23

 prove

0.23

èįī

0.23

Activations Density 0.017%

No Known Activations

This feature has no known activations.