INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_30.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.30.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 nipples

-0.26

çĶ³

-0.25

 reflex

-0.25

 contributing

-0.25

 diluted

-0.24

-header

-0.24

 nested

-0.24

-sensitive

-0.24

ãģ¨ãĤĬ

-0.23

dil

-0.23

POSITIVE LOGITS

çī©

0.29

á½°

0.29

smart

0.28

å¯¿

0.26

.isOn

0.25

æĻºèĥ½

0.25

å¹³å®ī

0.25

onian

0.25

åĲĮæĹ¶

0.24

gia

0.24

Activations Density 0.882%

No Known Activations

This feature has no known activations.