INDEX

Explanations

No Explanations Found

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

éĩİçĶŁ

-0.28

/repository

-0.27

ester

-0.26

çľĭä¸įåĩº

-0.26

 migr

-0.25

è®¡åĪĴçĶŁèĤ²

-0.25

è¿Ļæ®µ

-0.25

chie

-0.24

 poster

-0.24

dating

-0.23

POSITIVE LOGITS

 Necessary

0.30

cles

0.29

 inspection

0.26

*pow

0.26

 Designs

0.25

 inspect

0.25

 ÑģÑĤÐ¾Ð»

0.25

 Barn

0.24

azzo

0.24

 Inspection

0.24

Activations Density 0.013%

No Comments

No Known Activations