INDEX

Explanations

the

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

edly

-0.28

æ³Ľ

-0.26

ble

-0.25

aller

-0.25

 Clothing

-0.25

æĨ©

-0.24

 Nack

-0.24

é¦Ĭ

-0.23

subscription

-0.23

 Dane

-0.23

POSITIVE LOGITS

ä¸įæĢķ

0.28

iesen

0.28

=~

0.28

å¯Į

0.27

redirectTo

0.27

exus

0.27

 migrate

0.27

 integration

0.26

wards

0.26

ç¬¬ä¸īä»£

0.26

Activations Density 0.013%

the

No Comments

No Known Activations