INDEX

Explanations

pl

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ulerAngles

-0.26

__).

-0.26

 interp

-0.25

Ø¬ÙħÙĩ

-0.25

åĲīåĪ©

-0.25

alist

-0.25

_finalize

-0.24

 Trader

-0.24

 baker

-0.24

æ¬¡ä¼ļè®®

-0.24

POSITIVE LOGITS

land

0.29

 Land

0.28

èįī

0.28

det

0.27

det

0.27

lan

0.27

éªļ

0.26

uga

0.26

 Customs

0.25

Land

0.25

Activations Density 0.009%

pl

No Known Activations