INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

uur

-0.29

éĩĿ

-0.26

alse

-0.26

 Grove

-0.26

=r

-0.25

 genuinely

-0.25

áº¿u

-0.24

lyph

-0.24

å®ŀè´¨

-0.24

udu

-0.24

POSITIVE LOGITS

èĬ±æł·

0.26

.setStatus

0.25

åİ©

0.24

åįģå¹´

0.24

 outlaw

0.23

DK

0.23

çī©çĲĨåŃ¦

0.23

ä½ĵåŀĭ

0.23

ç»°

0.23

ä¸Ģæīĭ

0.23

Activations Density 21.258%

No Known Activations

This feature has no known activations.