INDEX

Explanations

web content

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

fer

-0.30

éķĢéĶĮ

-0.29

 depths

-0.28

Fer

-0.28

fer

-0.27

 tune

-0.26

èĤ¤

-0.26

reg

-0.26

POSITIVE LOGITS

 scramble

0.32

 COPYRIGHT

0.29

åħ±åĪĽ

0.28

.Weight

0.26

shoot

0.25

-floating

0.24

 oversh

0.24

verity

0.24

 useForm

0.24

æľ¬æĬ¥è®¯

0.23

Activations Density 0.001%

web content

No Comments

No Known Activations