INDEX

Explanations

out

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.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

è¿Ĳ

-0.29

åĳ½

-0.28

éģĭ

-0.28

çĽ®

-0.27

icken

-0.26

éī´

-0.26

åĬŁ

-0.26

çªģ

-0.26

etermine

-0.25

æĪĲä¸º

-0.25

POSITIVE LOGITS

è´µå®¾

0.28

èİº

0.27

æľ¬æĿ¥å°±

0.26

.toObject

0.25

 wholesale

0.25

Sidebar

0.25

éĻĤ

0.25

 Sidebar

0.24

boxes

0.24

 geli

0.24

Activations Density 45.886%

out

No Comments

No Known Activations