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

ä¸ĩæĪ·

-0.33

å¼Ģ

-0.25

å¿µå¤´

-0.24

 ||↵

-0.24

çĤ¹å¤ļ

-0.24

ahrungen

-0.23

uml

-0.23

 setUsername

-0.23

umm

-0.23

ki

-0.23

POSITIVE LOGITS

çľĭä¸įåĩº

0.29

·æĸ°

0.29

 Pais

0.27

 respective

0.26

åģļå®Į

0.26

POSIT

0.26

æĹłæĥħ

0.26

 sprzÄĻ

0.25

postData

0.25

apult

0.25

Activations Density 0.001%

No Known Activations

This feature has no known activations.