INDEX

Explanations

the

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ķ

-0.28

Ã¡p

-0.26

lotte

-0.25

ialized

-0.24

erman

-0.24

å¤¯

-0.24

 traded

-0.24

ç«¦

-0.24

-valid

-0.23

uese

-0.23

POSITIVE LOGITS

 Revision

0.27

otch

0.26

Revision

0.26

ÐºÐ»Ð°

0.26

 Reeves

0.26

å¸Ī

0.25

CRS

0.24

oser

0.24

èĥĮçĿĢ

0.24

áº¡t

0.24

Activations Density 0.003%

the

No Comments

No Known Activations