INDEX

Explanations

Code and technical language

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

çķİ

-0.28

åĬĪ

-0.26

éĻĦåĬł

-0.25

.tk

-0.25

 Harvest

-0.25

é»ĺè®¤

-0.25

ìłĪ

-0.24

abs

-0.24

:".

-0.24

 Farm

-0.23

POSITIVE LOGITS

|RF

0.27

éĥ½æĥ³

0.27

ä¹Ī

0.26

atile

0.26

éĢĨè¡Į

0.25

atisfied

0.25

ä¿¡æģ¯åıĳå¸ĥ

0.24

angible

0.24

woocommerce

0.24

çļĦéĴ±

0.24

Activations Density 0.001%

Code and technical language

No Comments

No Known Activations