INDEX

Explanations

named entities

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ing

-0.30

ä¸ĩçī©

-0.30

am

-0.28

int

-0.27

 committed

-0.27

 comparative

-0.26

 Comparative

-0.25

åĲĦç±»

-0.25

pe

-0.25

çī©

-0.24

POSITIVE LOGITS

åļĵ

0.28

rud

0.28

rup

0.27

è¿Ļç§įäºĭæĥħ

0.27

åĭº

0.26

æ³Į

0.26

ney

0.26

apos

0.25

è¦ģçŁ¥éģĵ

0.25

æ¯ıä¸ªäººçļĦ

0.24

Activations Density 0.786%

named entities

No Comments

No Known Activations