INDEX

Explanations

ine

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

åıĹå®³èĢħ

-0.28

æĹ¢çĦ¶

-0.27

åıĹå®³

-0.26

 jspb

-0.26

Colon

-0.26

_fraction

-0.25

åıĹçĽĬ

-0.25

?):

-0.25

 laure

-0.25

%C

-0.25

POSITIVE LOGITS

æħİ

0.31

å§Ķ

0.27

>Loading

0.26

-clean

0.26

 aroma

0.26

 equiv

0.25

 equival

0.25

ulus

0.25

ç¥Ĺ

0.25

arring

0.24

Activations Density 0.010%

ine

No Comments

No Known Activations