INDEX

Explanations

viewing/cutting

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

æµĬ

-0.29

[]=$

-0.27

 Operation

-0.26

æ°Ķæģ¯

-0.26

 delegated

-0.25

reten

-0.25

 blades

-0.25

 operation

-0.24

ç¤¼

-0.24

Operation

-0.24

POSITIVE LOGITS

ë°ĺ

0.29

ply

0.27

ä¸¾ä¾ĭ

0.25

éģŃåıĹ

0.25

åħ³

0.24

 finalist

0.24

ÑģÑĤÐ°Ð½

0.24

-cent

0.23

modo

0.23

-watch

0.23

Activations Density 0.181%

viewing/cutting

No Comments

No Known Activations