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

baseUrl

-0.29

abay

-0.29

uilder

-0.25

ç¶²çµ¡

-0.24

æ¦Ĥå¿µèĤ¡

-0.24

 Ã¡n

-0.23

åİ»æī¾

-0.23

{return

-0.23

::$

-0.23

beits

-0.23

POSITIVE LOGITS

 getProperty

0.27

isol

0.26

Aur

0.26

oder

0.26

oth

0.25

çĸ

0.25

edy

0.25

sp

0.25

lo

0.25

 October

0.24

Activations Density 0.021%

No Known Activations

This feature has no known activations.