INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

cx

-0.28

Dud

-0.27

 Vand

-0.26

late

-0.25

ez

-0.24

pil

-0.24

 late

-0.24

à¹Ģà¸Ħ

-0.24

 Cure

-0.24

 Operators

-0.24

POSITIVE LOGITS

 contends

0.27

 dotyczÄħ

0.26

Ã¼rn

0.26

istant

0.25

 kiá»ĩn

0.24

æĶ»åĿļæĪĺ

0.24

âĶ´

0.24

itant

0.24

 nationwide

0.23

ocaust

0.23

Activations Density 0.000%

No Comments

No Known Activations