INDEX

Explanations

Dec

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 myth

-0.27

 bacter

-0.26

éĿ©

-0.26

istor

-0.26

 nháº¥t

-0.25

 cÃ©

-0.25

Ð¼Ñı

-0.25

æłĩæ³¨

-0.25

ille

-0.24

 caul

-0.24

POSITIVE LOGITS

æģĭäºº

0.26

AndView

0.26

ilibrium

0.25

ä¸įå®¹

0.24

.va

0.24

dsp

0.24

å¹´äºº

0.24

çĽ¸äº²

0.23

æħĪåĸĦ

0.23

eam

0.23

Activations Density 0.001%

Dec

No Comments

No Known Activations