INDEX

Explanations

requesting something/someone

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åŁİå¸Ĥåıĳå±ķ

-0.32

åŁİå¸Ĥå»ºè®¾

-0.31

corn

-0.28

èĩªè´Ł

-0.28

 Eastern

-0.26

åŁİå¸Ĥ

-0.25

å¿ĺ

-0.25

aru

-0.24

commerce

-0.24

éĩįçĤ¹åħ³æ³¨

-0.24

POSITIVE LOGITS

ohana

0.29

æīĳ

0.28

DOI

0.27

 spheres

0.26

ovich

0.26

ais

0.26

agit

0.25

beiten

0.24

 sphere

0.24

 complement

0.23

Activations Density 0.022%

requesting something/someone

No Comments

No Known Activations