INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 :↵↵↵↵

-0.30

Term

-0.27

å®£

-0.25

icone

-0.24

 Term

-0.23

utions

-0.23

INESS

-0.23

SYNC

-0.23

 term

-0.23

 niche

-0.23

POSITIVE LOGITS

è¿ĻæĿ¡

0.26

arend

0.26

å¦ĤæľŁ

0.25

Programming

0.25

 Commonwealth

0.25

 Programming

0.25

æ¦´

0.25

 powsta

0.24

crawl

0.24

tracts

0.24

Activations Density 0.196%

No Known Activations

This feature has no known activations.