INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

ãģĬãģĭ

-0.28

 Locator

-0.25

 Locate

-0.25

ç¹

-0.24

 technically

-0.24

 Terrace

-0.24

 Pret

-0.24

Represent

-0.24

è°Ń

-0.24

uctive

-0.24

POSITIVE LOGITS

ilen

0.31

 union

0.29

union

0.27

åĵģ

0.26

tip

0.26

oined

0.25

tra

0.25

 pass

0.24

æŃ£ç¡®çļĦ

0.24

âĪ

0.24

Activations Density 0.048%

No Known Activations

This feature has no known activations.