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

lamp

-0.27

peaker

-0.27

ecast

-0.26

ibilities

-0.25

asad

-0.24

ä¸īç§į

-0.24

å®£è®²

-0.24

Ð»ÑİÐ´

-0.24

ä¸Ģå¹ķ

-0.23

InMillis

-0.23

POSITIVE LOGITS

 Venue

0.30

æĢģåº¦

0.29

gel

0.28

åĬ¨ä½ľ

0.27

éĥħ

0.26

 Sommer

0.26

åģı

0.25

åĭķä½ľ

0.25

ayah

0.25

æĭĸ

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.