INDEX

Explanations

ï¼ī

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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¸įå±ŀäºİ

-0.26

atchet

-0.25

æ¢³

-0.25

pun

-0.25

 grooming

-0.25

<!

-0.24

åĨĻä½ľ

-0.24

MLS

-0.23

ç½®èº«

-0.23

pose

-0.23

POSITIVE LOGITS

Lots

0.29

ÅĤad

0.28

lÃ¤ss

0.28

åħ³äºİæĪĳä»¬

0.28

èĦĨ

0.27

åķĨæĬ¥

0.27

Ã¡z

0.26

ÐµÑĢÐµ

0.26

 SEAL

0.26

 Lots

0.26

Activations Density 0.004%

ï¼ī

No Comments

No Known Activations