INDEX

Explanations

html

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ingly

-0.28

 PROP

-0.25

SpaceItem

-0.25

auty

-0.25

æķĸ

-0.23

abb

-0.23

 tranqu

-0.22

æł¹æį®èĩªå·±

-0.22

ably

-0.22

 dirig

-0.22

POSITIVE LOGITS

åħĳ

0.28

/XML

0.26

DivElement

0.25

ä¹ĭæĺŁ

0.24

Major

0.24

ting

0.24

è½¬å¼¯

0.24

viz

0.24

ness

0.23

éĹªçĥģ

0.23

Activations Density 0.404%

html

No Comments

No Known Activations