INDEX

Explanations

radiation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ÄĻp

-0.27

ç´§

-0.27

")[

-0.26

åĨįåĬłä¸Ĭ

-0.26

isp

-0.26

dru

-0.25

vÃª

-0.25

')[

-0.24

emplo

-0.24

ewe

-0.24

POSITIVE LOGITS

æĶ¾

0.30

arkan

0.27

åī©

0.27

ä¸Ĭä¼ł

0.26

ĤŃ

0.25

 meaning

0.25

meaning

0.25

 blanket

0.24

çĶŁåĳ½

0.23

éģ¿åħį

0.23

Activations Density 0.060%

radiation

No Comments

No Known Activations