INDEX

Explanations

information

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Poss

-0.26

çĽ²

-0.26

çĶĺ

-0.26

bur

-0.25

æĻĭçº§

-0.25

*pow

-0.25

 Poss

-0.24

æĳĨèĦ±

-0.24

pow

-0.24

å£ģåŀĴ

-0.24

POSITIVE LOGITS

æĸĩä¸Ń

0.26

 advert

0.26

è¿ĺæľīä¸Ģä¸ª

0.25

æĪĳè¿ĺæĺ¯

0.25

Ã¡ndez

0.25

æĺİé¡¯

0.25

arer

0.25

 likely

0.25

ä½ĵçİ°äºĨ

0.24

fram

0.24

Activations Density 0.077%

information

No Comments

No Known Activations