INDEX

Explanations

vegetable

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

ç»ı

-0.29

 divisions

-0.28

 Corps

-0.28

Naw

-0.26

//-

-0.26

ente

-0.26

 kernels

-0.26

ingu

-0.25

ency

-0.25

ipse

-0.25

POSITIVE LOGITS

ron

0.31

icular

0.28

ose

0.27

ä¸ı

0.25

ee

0.25

ç²±

0.25

åĲįçīĩ

0.24

 Attach

0.24

ress

0.24

de

0.24

Activations Density 0.045%

vegetable

No Comments

No Known Activations