INDEX

Explanations

Randomness

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

 stem

-0.29

 furnace

-0.27

Ä±nÄ±n

-0.27

erin

-0.27

ä¸įä¸Ģæł·çļĦ

-0.26

stem

-0.25

åı²è¯Ĺ

-0.25

ÃŁen

-0.25

æ¯¯

-0.25

åī¯ä¹¦è®°

-0.24

POSITIVE LOGITS

.ide

0.28

è§ģåĪ°

0.25

<?↵

0.25

 tÆ°á»£ng

0.24

PLIC

0.24

ophil

0.23

.–

0.23

ettel

0.23

ç²¾ç¥ŀæĸĩæĺİ

0.23

åĪĽæĸ°èĥ½åĬĽ

0.23

Activations Density 14.074%

Randomness

No Comments

No Known Activations