INDEX

Explanations

New South Wales

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

<<-

-0.30

Jeh

-0.29

 Voices

-0.27

Ã´

-0.27

 empir

-0.26

ful

-0.26

usta

-0.25

$__

-0.25

(/^

-0.24

å¼Ģåħĥ

-0.24

POSITIVE LOGITS

phia

0.30

afs

0.29

 personal

0.29

åľ°ä¸Ń

0.28

.getColumn

0.27

åľ°

0.27

personal

0.26

asma

0.25

zac

0.25

ä¿ĿéĻ©

0.25

Activations Density 0.002%

New South Wales

No Comments

No Known Activations