INDEX

Explanations

product features

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ention

-0.26

 Hydra

-0.26

åŃ£åĲİ

-0.25

ç¬¬ä¸Ģæī¹

-0.25

 immedi

-0.25

ä¸Ģå®ļçļĦ

-0.24

éĥ¨åĪĨåĨħå®¹

-0.24

 imminent

-0.24

æ¯ıä¸Ģå¤©

-0.23

æµª

-0.23

POSITIVE LOGITS

 compared

0.37

ä¸Ķ

0.28

 even

0.28

AFF

0.27

å¹¶ä¸Ķ

0.27

 brighter

0.26

 directional

0.26

ï¼Įå¹¶

0.25

ä¹Łæ¯Ķè¾ĥ

0.25

enh

0.25

Activations Density 0.005%

product features

No Comments

No Known Activations