INDEX

Explanations

free

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

 Wrapped

-0.26

Wrapped

-0.26

virtual

-0.26

 gradu

-0.26

pace

-0.25

åıĳçİ°èĩªå·±

-0.25

ä¸įèµ·

-0.25

raise

-0.24

åħľ

-0.24

wick

-0.24

POSITIVE LOGITS

annel

0.29

é«ĺæ°´å¹³

0.28

arbon

0.28

avn

0.26

ffield

0.25

anean

0.24

çĽĨ

0.23

avar

0.23

 arab

0.23

iances

0.23

Activations Density 0.013%

free

No Comments

No Known Activations