INDEX

Explanations

Numbers

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

forme

-0.27

_vlog

-0.27

HEEL

-0.27

éĹªçĥģ

-0.26

ager

-0.26

ware

-0.26

å¾ĢåĲİ

-0.26

Ð½ÐµÑĢ

-0.25

è½¬åıĳ

-0.25

anas

-0.25

POSITIVE LOGITS

uju

0.28

 Granny

0.28

_permalink

0.24

è¸½

0.24

BX

0.24

$arr

0.24

abyrinth

0.24

ä¹ĺçĶ¨è½¦

0.24

.FC

0.23

åĽ½å®¶æłĩåĩĨ

0.23

Activations Density 0.040%

Numbers

No Comments

No Known Activations