INDEX

Explanations

named locations

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

iveau

-0.26

-preview

-0.25

<Task

-0.24

æĴķ

-0.24

.displayName

-0.24

 Owner

-0.23

 Athens

-0.23

à¸²à¸§

-0.23

âĢĴ

-0.23

inear

-0.23

POSITIVE LOGITS

{}.

0.30

 Armour

0.26

åĳ½

0.25

éĩįè¦ģåİŁåĽł

0.25

åĳ½ä¸Ń

0.25

riz

0.24

å¸ĪèµĦ

0.24

æĿ¡ä»¶

0.24

æĭĽèģĺä¿¡æģ¯

0.24

Ñŀ

0.23

Activations Density 0.009%

named locations

No Comments

No Known Activations