INDEX

Explanations

//------------------------------------------------------------------------------

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

iver

-0.28

æĻĴ

-0.27

upa

-0.26

 write

-0.26

chner

-0.25

 Cave

-0.24

vince

-0.24

 pleasant

-0.24

 cave

-0.24

ķĮ

-0.24

POSITIVE LOGITS

BERS

0.31

OMPI

0.26

æģ¢

0.26

è´¨

0.26

ORS

0.26

åĲĮæ¯Ķ

0.25

åıĳå±ķç©ºéĹ´

0.25

èĮ«

0.25

stag

0.25

åĲĪæ³ķæĢ§

0.25

Activations Density 0.095%

//------------------------------------------------------------------------------

No Comments

No Known Activations