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

Negative Logits

ä»ĵ

-0.28

ç®ĹäºĨ

-0.27

çĻ¾ç§ĳ

-0.25

iddy

-0.25

å¿¿

-0.25

æī¬

-0.25

æĸĩæ¡£

-0.24

çº¢æĹĹ

-0.24

æ¹

-0.24

endency

-0.24

POSITIVE LOGITS

çŃīçĿĢ

0.25

 Blackburn

0.24

çĨı

0.24

 transfers

0.24

.br

0.23

å¼Ģä¸ļ

0.23

 McGu

0.23

guid

0.23

Br

0.23

æĮĩå¯¼ä¸ĭ

0.23

Activations Density 16.144%

the

No Known Activations