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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åŁºæķ°

-0.30

sie

-0.27

ħ§

-0.26

åĹ¨

-0.26

APO

-0.26

asers

-0.25

æ³ķå®ļ

-0.25

åħ¹

-0.24

aw

-0.24

sie

-0.24

POSITIVE LOGITS

anni

0.30

morgan

0.27

xCF

0.26

<![

0.26

ynet

0.26

-mount

0.25

ourd

0.25

 cancers

0.25

æīĭä¸Ĭ

0.24

ÑģÐ°Ð´

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.