INDEX

Explanations

the

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

éĺľ

-0.27

 –↵↵

-0.27

.branch

-0.25

-turned

-0.25

Ã©ra

-0.24

èµ´

-0.23

zej

-0.23

enos

-0.23

èĬ³

-0.23

-fat

-0.23

POSITIVE LOGITS

Foot

0.28

beg

0.28

.cum

0.26

 atleast

0.26

éĩįè¦ģåĽłç´ł

0.25

Secure

0.25

éĹ´éļĻ

0.24

 Secure

0.24

lies

0.24

beg

0.23

Activations Density 2.114%

the

No Comments

No Known Activations