INDEX

Explanations

really actually

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

å¿ĥä¸ŃçļĦ

-0.29

neh

-0.29

-through

-0.28

egas

-0.28

edo

-0.27

Ã¶n

-0.27

é¦ĸä½į

-0.27

)<<

-0.27

'||

-0.26

æĦıæĢĿ

-0.26

POSITIVE LOGITS

å¬ĸ

0.29

å¤«å¦ĩ

0.27

icult

0.26

 getItem

0.25

ä¸ŃåĽ½æ±½è½¦

0.25

 currentItem

0.25

íķŃ

0.25

woff

0.24

åĲĮè¡Į

0.24

ree

0.24

Activations Density 0.004%

really actually

No Comments

No Known Activations