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

duplicate

-0.28

enders

-0.25

æ¯ıæĹ¥

-0.25

roller

-0.25

çļĦæĦıä¹ī

-0.24

walker

-0.24

precated

-0.23

çºĤ

-0.23

ashed

-0.23

 Runner

-0.23

POSITIVE LOGITS

vez

0.27

 gums

0.25

ags

0.25

é¦ģ

0.24

åħ¸åŀĭ

0.24

 materials

0.23

MV

0.23

-inf

0.23

á»£

0.23

unker

0.23

Activations Density 0.034%

No Known Activations

This feature has no known activations.