INDEX

Explanations

Articles/of

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĲįåŃĹ

-0.49

 names

-0.46

 name

-0.43

çļĦåĲįåŃĹ

-0.42

-name

-0.39

åĲįç§°

-0.39

 naming

-0.38

 Names

-0.37

å§ĵåĲį

-0.36

names

-0.35

POSITIVE LOGITS

0.28

ä»İæł¹æľ¬ä¸Ĭ

0.27

é©±

0.26

èģĮä¸ļæĬĢæľ¯

0.26

åĩŃ

0.26

çŃĸ

0.25

åłĨ

0.25

å¤ĩ

0.24

tour

0.24

ç§¯

0.24

Activations Density 0.002%

Articles/of

No Comments

No Known Activations