INDEX

Explanations

yl

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

æ°ĺ

-0.31

 flick

-0.29

 Äĳá»ı

-0.25

dden

-0.25

 ÑĥÑģÑĤÐ°Ð½Ð¾Ð²Ð»ÐµÐ½

-0.25

 curs

-0.24

 gone

-0.24

 upon

-0.23

verted

-0.23

IGO

-0.23

POSITIVE LOGITS

mos

0.28

angles

0.26

æł¹

0.26

ilateral

0.25

Nam

0.25

ibia

0.24

vÃ©

0.24

ordion

0.24

indrical

0.24

ilinear

0.24

Activations Density 1.115%

yl

No Comments

No Known Activations