INDEX

Explanations

biographies

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ç¹ģå¿Ļ

-0.27

.training

-0.27

å·¥ä½ľçļĦ

-0.27

 ÑģÐºÐ°Ñĩ

-0.26

iges

-0.26

egree

-0.26

 grad

-0.26

æĥħåĨµæĿ¥çľĭ

-0.25

manent

-0.25

 priesthood

-0.25

POSITIVE LOGITS

born

0.33

åĢĻéĢīäºº

0.30

dbl

0.28

 bÃ¨

0.27

éģĵ

0.27

å¯¹æīĭ

0.27

“She

0.26

åı¦ä¸Ģä½į

0.26

 doctrine

0.26

 Doctrine

0.25

Activations Density 0.008%

biographies

No Comments

No Known Activations