INDEX

Explanations

2

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

tail

-0.30

Wid

-0.30

 tail

-0.29

 duty

-0.28

acock

-0.27

phet

-0.27

qtt

-0.26

æľĢç¾İ

-0.26

 deut

-0.25

èĥĢ

-0.25

POSITIVE LOGITS

 selectedItem

0.28

.SelectedItems

0.27

 onSelect

0.26

 renderItem

0.26

 Giov

0.26

ä¸Ģç±»

0.25

 payloads

0.25

fÃ¤hig

0.24

éĢīå®ļ

0.24

/framework

0.24

Activations Density 0.002%

2

No Comments

No Known Activations