INDEX

Explanations

role

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç¾¤

-0.30

é²ľèĬ±

-0.28

æİĮæı¡

-0.27

çļĦåŁºç¡Ģä¸Ĭ

-0.25

 aÃ§Ä±k

-0.25

ç»ĵæŀĦæĢ§

-0.24

osit

-0.24

åİļ

-0.24

ä½İäºİ

-0.24

ictionaries

-0.23

POSITIVE LOGITS

çĢĽ

0.27

ungan

0.26

 Ð¿Ð¾ÑģÐ»

0.25

 discrimin

0.24

attended

0.24

 bridal

0.24

 quot

0.23

 championship

0.23

apped

0.23

ows

0.23

Activations Density 6.540%

role

No Comments

No Known Activations