INDEX

Explanations

years

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

 monthly

-0.32

æľĪæľ«

-0.29

æ¯ıæľĪ

-0.29

April

-0.28

åħ¨å¹´

-0.28

 yearly

-0.28

 annual

-0.27

uo

-0.27

 July

-0.27

 weekly

-0.27

POSITIVE LOGITS

éĥĽ

0.30

åľĨå½¢

0.27

 innoc

0.27

 instrument

0.27

instrument

0.27

è¾±

0.27

æĪ¿éĹ´éĩĮ

0.26

.addAttribute

0.26

åĹ£

0.25

 consciously

0.25

Activations Density 0.001%

years

No Comments

No Known Activations