INDEX

Explanations

commas

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

gere

-0.29

æ³¼

-0.28

xis

-0.27

ä¹¡

-0.27

nis

-0.27

 uncle

-0.26

åĦ¿åŃĲ

-0.25

 brother

-0.25

è®©å®ĥ

-0.25

—he

-0.25

POSITIVE LOGITS

/sdk

0.34

å®¤

0.32

bez

0.28

+-+-+-+-

0.26

ä¸Ģä½ĵ

0.26

å¤ªå¹³æ´ĭ

0.25

å¯ĨéĽĨ

0.24

 inaug

0.24

éķĿ

0.24

Exposed

0.24

Activations Density 0.079%

commas

No Comments

No Known Activations