INDEX

Explanations

0

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pty

-0.30

æ¼«

-0.29

whole

-0.28

ERY

-0.28

 whole

-0.27

unkt

-0.27

atham

-0.26

å¹´å¼Ģå§ĭ

-0.26

subplot

-0.25

 landed

-0.24

POSITIVE LOGITS

eness

0.29

ibility

0.29

ibilidade

0.29

abilities

0.27

Voy

0.26

æĮĩæķ°

0.26

ibilidad

0.25

leness

0.25

bern

0.24

jec

0.24

Activations Density 0.003%

0

No Comments

No Known Activations