INDEX

Explanations

wake

np_max-act-logits · gemini-2.0-flash

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

rep

-0.32

 heat

-0.28

 Uncomment

-0.27

ros

-0.26

res

-0.25

 perm

-0.25

esti

-0.25

xes

-0.25

re

-0.25

educt

-0.24

POSITIVE LOGITS

é¦ģ

0.29

Shock

0.27

æĢİä¹Īè¯´

0.26

çİ©

0.24

validation

0.24

ÐŁÐµÑĤ

0.24

over

0.23

éº»çĹ¹

0.23

flix

0.23

åĽłç´ł

0.23

Activations Density 0.190%

wake

No Comments

No Known Activations