INDEX

Explanations

Industries and Technologies

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_0.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.0.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ForObject

-0.26

incare

-0.25

ä¹Łåıªæľī

-0.25

asket

-0.25

ramework

-0.25

 amid

-0.24

searchModel

-0.24

akov

-0.24

 Affero

-0.24

etheless

-0.23

POSITIVE LOGITS

åı£æľį

0.28

åı¯èĥ½æĢ§

0.27

pers

0.26

Mix

0.25

uÃ©

0.24

gal

0.24

åĸ·

0.23

kor

0.23

 shaken

0.23

Or

0.23

Activations Density 8.019%

Industries and Technologies

No Comments

No Known Activations