INDEX

Explanations

forum posts, code

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å£³

-0.26

åħ»

-0.25

æį·

-0.25

ä¸įå¾Ĺä¸įè¯´

-0.25

idis

-0.24

âĶĦ

-0.24

 imaginable

-0.24

kul

-0.24

çļĦæĸ¹å¼ıæĿ¥

-0.24

orate

-0.24

POSITIVE LOGITS

above

0.30

Above

0.30

ä»¥ä¸Ĭ

0.29

 above

0.28

ä¸Ĭè¿°

0.28

 Above

0.27

ä¸ĬéĿ¢

0.27

 *)↵↵

0.26

 pertinent

0.25

saving

0.25

Activations Density 0.317%

forum posts, code

No Comments

No Known Activations