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

åħ·æľīä¸Ģå®ļ

-0.29

åŃº

-0.29

anth

-0.29

enha

-0.25

olland

-0.25

à°Ĩ

-0.25

mere

-0.25

UI

-0.24

ãģ¦ãģĦ

-0.24

 seemingly

-0.24

POSITIVE LOGITS

 rewriting

0.34

á»įng

0.26

PCODE

0.26

-Allow

0.25

ìĿĢ

0.25

%-

0.24

 resh

0.24

-bind

0.23

éļĲ

0.23

Ã¡m

0.22

Activations Density 0.005%

No Known Activations

This feature has no known activations.