INDEX

Explanations

)

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

åĴĮä¸ªäºº

-0.31

bower

-0.29

åıĪèĥ½

-0.27

åŃ½

-0.27

TY

-0.26

åº¶

-0.26

éĢłæĪĲ

-0.25

èµŀåĬ©

-0.25

çļĦæłĩåĩĨ

-0.25

atorial

-0.24

POSITIVE LOGITS

uentes

0.26

 Cour

0.26

æĥ³

0.26

éĨī

0.26

az

0.25

 bucket

0.25

pie

0.24

é©¬

0.24

ensem

0.24

vir

0.24

Activations Density 0.004%

)

No Comments

No Known Activations