INDEX

Explanations

programming and math problems

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

ä¼łæī¿

-0.27

at

-0.26

å½¢

-0.26

etto

-0.26

athon

-0.25

ãĤīãģĦ

-0.24

ä»²

-0.24

æĪĳä»¬è®¤ä¸º

-0.24

æĹ¥æ¶Īæģ¯

-0.24

phe

-0.24

POSITIVE LOGITS

å¦ª

0.26

 succeeded

0.26

ca

0.24

ä¼İ

0.24

FIL

0.24

lish

0.24

ç³ģ

0.23

èĲĺ

0.23

utta

0.23

pa

0.23

Activations Density 47.579%

programming and math problems

No Comments

No Known Activations