INDEX

Explanations

2008

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

personal

-0.28

atest

-0.27

Personal

-0.26

recent

-0.26

Ut

-0.25

nah

-0.24

 predator

-0.24

deny

-0.24

BED

-0.24

 Nichols

-0.23

POSITIVE LOGITS

Ã¸d

0.29

ilda

0.27

ewolf

0.26

çīį

0.26

.deleteById

0.25

 addChild

0.25

åıĳå¸ĥåħ¬åĳĬ

0.25

aoke

0.25

hexdigest

0.25

.Download

0.24

Activations Density 0.001%

2008

No Comments

No Known Activations