INDEX

Explanations

credits/entries

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

æľīçļĦäºº

-0.30

çĦ¶æĺ¯

-0.28

 Britt

-0.26

 bonds

-0.26

åĲĮå¿ĥ

-0.25

 grind

-0.25

mort

-0.25

å¤§å¤§å°ı

-0.25

wear

-0.25

 Bonds

-0.24

POSITIVE LOGITS

herit

0.32

 nast

0.29

formation

0.27

å°ıç¼ĸ

0.27

æ³

0.27

ä¸Ńæłĩ

0.26

lob

0.26

 typeid

0.25

 heritage

0.25

LOB

0.24

Activations Density 0.012%

credits/entries

No Comments

No Known Activations