INDEX

Explanations

Code, research, technical texts

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

cona

-0.31

æŃ¤åŁºç¡Ģä¸Ĭ

-0.30

çļĦéĤ£ä¸ª

-0.29

ASA

-0.28

çļĦèµĦéĩĳ

-0.27

 Trá»įng

-0.26

 excit

-0.26

 bitcoins

-0.25

."""↵↵

-0.25

éķ¿éķ¿

-0.24

POSITIVE LOGITS

è®¯

0.28

0.26

rick

0.25

’

0.25

Similarly

0.25

ãĥĭãĥ³ãĤ°

0.25

imer

0.25

 Simple

0.25

åŁİå¸ĤçļĦ

0.24

èĩªåªĴä½ĵ

0.24

Activations Density 0.001%

Code, research, technical texts

No Comments

No Known Activations