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

fram

-0.31

ups

-0.29

aking

-0.27

åİĭå®ŀ

-0.27

 ì§

-0.26

æ´»

-0.26

upt

-0.25

ls

-0.25

è¯´åĪ°

-0.24

POSITIVE LOGITS

æ²¹èĦĤ

0.30

 firefox

0.26

(hour

0.26

åįİçĽĽ

0.26

 BigInt

0.25

 xmlDoc

0.25

NotificationCenter

0.24

æ´¥è´´

0.24

 Nights

0.24

 IndexPath

0.24

Activations Density 0.003%

No Comments

No Known Activations