INDEX

Explanations

prepositions

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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

accuracy

-0.29

Ã±e

-0.28

çĩ®

-0.27

emp

-0.26

 accuracy

-0.25

 Gesch

-0.25

æķĪçİĩ

-0.25

 precision

-0.25

 growth

-0.25

å¢ŀéķ¿çİĩ

-0.25

POSITIVE LOGITS

stag

0.32

ä¸īåĪĨ

0.28

è¿Ľä¸ĢæŃ¥

0.28

seo

0.26

ä¿Ŀåģ¥

0.26

å¯Įæľī

0.25

éĢ²ä¸ĢæŃ¥

0.25

ä¿Ŀå®ī

0.25

urther

0.25

åĪ¨

0.25

Activations Density 0.023%

prepositions

No Comments

No Known Activations