INDEX

Explanations

copyright

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

æĿłæĿĨ

-0.30

ky

-0.27

çĭ¬çī¹çļĦ

-0.26

 endors

-0.26

 decisive

-0.26

 Downs

-0.25

},{"

-0.25

æŀĦæĪĲ

-0.25

 Prest

-0.25

 Mavericks

-0.25

POSITIVE LOGITS

åİŁæĸĩåľ°åĿĢ

0.28

æľ¬ç¶²ç«Ļ

0.27

æ®ĩ

0.25

è¿ĺä¸įå¦Ĥ

0.25

æĥħ

0.25

emes

0.25

_matrices

0.24

orld

0.24

 Ð¸ÑģÑĤ

0.24

ailed

0.24

Activations Density 0.020%

copyright

No Comments

No Known Activations