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

æĥ³èµ·æĿ¥

-0.28

å®ŀéĻħä¸Ĭ

-0.25

ngine

-0.24

æĮ½

-0.24

UIP

-0.24

ificial

-0.24

yps

-0.24

EP

-0.24

 Slater

-0.24

 Scrap

-0.24

POSITIVE LOGITS

 Ð´ÐµÐ½

0.30

æ»´

0.26

ercul

0.26

-cond

0.26

_drop

0.25

 orientation

0.25

Ð°ÑĢÑĮ

0.25

çĲĨè§£åĴĮ

0.25

 warmer

0.25

 correspond

0.25

Activations Density 0.011%

No Known Activations

This feature has no known activations.