INDEX

Explanations

mass spectrometry

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 Corona

-0.27

spr

-0.25

oeff

-0.25

ä¸ªäº¤æĺĵ

-0.25

 overhead

-0.25

 fluorescence

-0.25

branches

-0.24

ãĥŀãĥ³

-0.24

 radiation

-0.24

 fluores

-0.24

POSITIVE LOGITS

IPC

0.35

IPC

0.30

åĪ»çĶ»

0.28

è¾Ľèĭ¦

0.27

irim

0.26

ipc

0.26

è®¤è¯Ĩ

0.26

 Leak

0.26

åŀĴ

0.26

éĽķåĪ»

0.25

Activations Density 0.897%

mass spectrometry

No Known Activations