INDEX

Explanations

quantities/emphasis

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

ignum

-0.26

odable

-0.26

SizePolicy

-0.26

ç»ĩ

-0.25

 Magnus

-0.25

Magn

-0.25

gard

-0.25

-0.24

ichi

-0.24

åı·

-0.24

POSITIVE LOGITS

tle

0.31

æµĥ

0.29

åİĿ

0.28

 apologies

0.26

çĴ§

0.25

æľįåĬ¡æ°´å¹³

0.25

åıĳæĮ¥

0.24

wal

0.24

 pilgr

0.24

 pavement

0.24

Activations Density 0.046%

quantities/emphasis

No Comments

No Known Activations