INDEX

Explanations

Contrasting ideas

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

">'

-0.27

'>"+

-0.27

 groupName

-0.26

æī«ä¸Ģæī«

-0.26

 Again

-0.26

ograf

-0.25

åįķåħĥ

-0.25

 testName

-0.25

 grou

-0.25

 freder

-0.25

POSITIVE LOGITS

åıĳçĹħ

0.30

æĢ§åĳ½

0.28

 relative

0.27

 KÃ¶n

0.26

achts

0.26

 translations

0.26

kak

0.26

.press

0.25

 press

0.25

semblies

0.25

Activations Density 0.040%

Contrasting ideas

No Comments

No Known Activations