INDEX

Explanations

reason

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

andes

-0.28

aise

-0.26

åĩĢ

-0.26

oso

-0.24

éĺ´

-0.24

 TypeError

-0.24

çĮĹ

-0.23

OfSize

-0.23

åĳ½åĳ¨æľŁ

-0.23

ÐµÑĩÐµÐ½Ð¸Ðµ

-0.23

POSITIVE LOGITS

ãģ£ãģĵ

0.27

awn

0.27

æĨ©

0.26

&q

0.26

 parch

0.25

awns

0.24

LTR

0.24

Ð´Ð²Ð¸Ð³

0.24

ocrat

0.24

$client

0.24

Activations Density 1.697%

reason

No Known Activations