INDEX

Explanations

Scientific/Taxonomic descriptions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 screens

-0.27

esti

-0.26

efs

-0.26

eps

-0.25

EPS

-0.25

çľĭå¥½

-0.25

ospital

-0.25

neg

-0.24

MemoryWarning

-0.24

_eps

-0.23

POSITIVE LOGITS

ÄĻ

0.30

 lá»£i

0.28

åħ¸åŀĭçļĦ

0.27

onium

0.26

æ²ª

0.26

ä¸ĥå¹´

0.24

è¿Ļä½į

0.24

 Differential

0.24

cow

0.23

asar

0.23

Activations Density 0.027%

Scientific/Taxonomic descriptions

No Comments

No Known Activations