INDEX

Explanations

Citations

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸īæĸ¹

-0.27

bound

-0.26

ur

-0.25

ç¦»èģĮ

-0.25

GDK

-0.25

fug

-0.24

 Vacation

-0.24

åĢŁ

-0.24

_bound

-0.24

åĢŁéĴ±

-0.24

POSITIVE LOGITS

åĪ©çī©

0.29

entr

0.27

entes

0.26

 Ð¿Ð¾ÑĢ

0.26

(step

0.24

ctr

0.24

 Norris

0.24

Lbl

0.24

æ¬¡è¦ģ

0.24

ksi

0.24

Activations Density 0.192%

Citations

No Comments

No Known Activations