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

DOWN

-0.26

æĤī

-0.26

 adjacent

-0.26

VERS

-0.26

 slightly

-0.24

adamente

-0.24

ewolf

-0.24

vic

-0.24

 Stevens

-0.24

ationToken

-0.23

POSITIVE LOGITS

å½Ĵ

0.26

éĹ®éĹ®

0.25

resource

0.25

åĽ½æĥħ

0.25

åĮ¹

0.25

live

0.24

æŀķå¤´

0.24

åĤ¬çĶŁ

0.24

 prelim

0.23

ä½ľçĶ¨

0.23

Activations Density 0.008%

No Known Activations

This feature has no known activations.