INDEX

Explanations

Code or system logs

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

 troch

-0.27

 coma

-0.25

Sup

-0.25

åľ¨è¿Ļæĸ¹éĿ¢

-0.24

çļĦå°±æĺ¯

-0.24

__)

-0.24

æĿ¥è¿ĻéĩĮ

-0.24

ISTA

-0.24

?]

-0.23

íĨ¤

-0.23

POSITIVE LOGITS

æľīåºıæİ¨è¿Ľ

0.27

URRE

0.26

yd

0.25

å¤·

0.25

ubbles

0.24

ç¬¬äºĮä¸ª

0.24

.lazy

0.24

ution

0.24

è¦ģåģļåĪ°

0.23

 chemicals

0.23

Activations Density 0.003%

Code or system logs

No Comments

No Known Activations