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

ap

-0.26

 masking

-0.25

WE

-0.25

Wa

-0.25

MS

-0.24

 blow

-0.23

 Bearings

-0.23

 attract

-0.23

 reload

-0.23

æ¹ĸåĮº

-0.23

POSITIVE LOGITS

odos

0.28

deo

0.27

â½¯

0.25

åĵ¦

0.25

enate

0.25

 Dedicated

0.23

åħ¬åĽŃ

0.23

æĽ¦

0.23

arlo

0.23

â¾ĥ

0.23

Activations Density 0.017%

No Known Activations

This feature has no known activations.