INDEX

Explanations

discussions opinions arguments

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĬ²

-0.31

åĭģ

-0.29

removeClass

-0.27

kest

-0.26

presso

-0.26

odia

-0.26

Nil

-0.25

à¹Ĥà¸Ł

-0.25

 scrim

-0.24

ä½İä¼°

-0.24

POSITIVE LOGITS

 accept

0.37

æİ¥åıĹ

0.37

 acceptance

0.36

è§ĦåĪĻ

0.33

æĿĥå¨ģ

0.32

 rÃ¨gle

0.32

/rules

0.31

æİĪæĿĥ

0.31

 abstract

0.30

 arbitrarily

0.30

Activations Density 0.001%

discussions opinions arguments

No Comments

No Known Activations