INDEX

Explanations

every

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åı¯æĺ¯

-0.30

åĿĲèĲ½äºİ

-0.29

theless

-0.28

çī¹çĤ¹æĺ¯

-0.28

åĬ±

-0.28

åĽĽä½į

-0.27

ä½Ĩæĺ¯ä»ĸ

-0.27

åį°åĪ·

-0.27

ä¸īä½į

-0.26

 Curso

-0.26

POSITIVE LOGITS

 whenever

0.46

 every

0.40

 Whenever

0.36

Whenever

0.35

æ¯ıå½ĵ

0.35

æ¯ıä¸Ģä¸ª

0.33

 Every

0.33

Every

0.33

 wherever

0.31

 Everywhere

0.29

Activations Density 0.009%

every

No Comments

No Known Activations