INDEX

Explanations

scenarios

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

 sworn

-0.28

å©¿

-0.26

 ÑĥÑģÐ¸Ð»Ð¸

-0.25

ew

-0.25

sted

-0.24

aware

-0.24

åħĥå®Ŀ

-0.24

 compensate

-0.23

decor

-0.23

 RequestContext

-0.23

POSITIVE LOGITS

å¥

0.28

 Grove

0.26

å¥Ī

0.25

æĭİ

0.25

 myself

0.25

 barrel

0.24

 suggestion

0.24

hang

0.24

é¢Ĺç²Ĵ

0.23

åĸĬ

0.23

Activations Density 0.004%

scenarios

No Comments

No Known Activations