INDEX

Explanations

first

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

 rearr

-0.26

enal

-0.26

 process

-0.26

 PrÃ¤

-0.25

èĦ±

-0.25

éĢģåĩº

-0.25

/rem

-0.25

 Trom

-0.25

process

-0.25

 relocated

-0.24

POSITIVE LOGITS

çļĦç«ŀäºī

0.27

ä¸ĢçĤ¹çĤ¹

0.26

ç«ŀ

0.26

çķ¸

0.25

æĬķæľº

0.25

ç«ŀäºī

0.24

 Casinos

0.24

å¸Ĥåľºç«ŀäºī

0.24

coop

0.24

.submit

0.24

Activations Density 0.018%

first

No Comments

No Known Activations