INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĮºåĨħ

-0.28

çļĦçĶŁæ´»

-0.26

çļĦå®¶åºŃ

-0.25

validated

-0.25

çļĦèº«ä½ĵ

-0.24

	super

-0.24

ç»¿åľ°

-0.24

æĶ¯çº¿

-0.24

inke

-0.24

æľĢéĢĤåĲĪ

-0.24

POSITIVE LOGITS

 Tell

0.30

åĳ½

0.29

Tell

0.28

 itemCount

0.27

 tell

0.26

iac

0.26

æ¥Ŀ

0.26

æĿ¡

0.25

tell

0.25

ITER

0.25

Activations Density 47.584%

No Known Activations

This feature has no known activations.