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

ä¸Ĭå¹´

-0.31

æĮĩå¯¼

-0.27

PV

-0.26

çİ°

-0.26

Prem

-0.25

Presentation

-0.25

 Bowman

-0.25

 presentation

-0.24

 Presentation

-0.24

 guidance

-0.23

POSITIVE LOGITS

enko

0.28

anda

0.26

 NodeType

0.26

èµ°åĪ°

0.26

uku

0.25

 recht

0.24

 hilar

0.24

 vite

0.24

 bottleneck

0.24

çªĴæģ¯

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.