INDEX

Explanations

universities and locations

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

adero

-0.25

åĲĳä¸ĭ

-0.24

 Hydro

-0.24

åĩºæ±Ĺ

-0.24

åĺĺ

-0.23

 hydro

-0.23

 Curtain

-0.23

 dáº§u

-0.23

åī©

-0.23

åī©ä½Ļ

-0.23

POSITIVE LOGITS

æł¹

0.31

kat

0.28

å¼ķæĵİ

0.28

Ð·Ð´

0.27

 engines

0.25

 suits

0.25

 Californ

0.25

egas

0.24

 scheme

0.24

 root

0.24

Activations Density 0.001%

universities and locations

No Comments

No Known Activations