INDEX

Explanations

Code/programming

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 accrued

-0.31

roken

-0.28

lems

-0.28

irmed

-0.28

edBy

-0.27

ä¸ºä¹ĭ

-0.26

 clientId

-0.26

ogens

-0.25

çİ©å®¶

-0.25

 countered

-0.25

POSITIVE LOGITS

 ranges

0.26

èĥª

0.25

æı£

0.25

 feeling

0.24

vie

0.24

æĺµ

0.24

ENA

0.24

or

0.24

ä¸Ĭæ¸¸

0.24

raits

0.24

Activations Density 4.861%

Code/programming

No Comments

No Known Activations