INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

ligt

-0.30

å±ħ

-0.28

åºķ

-0.27

èı¹

-0.26

 facil

-0.26

ContentSize

-0.26

å°±è¿ĳ

-0.26

 squeeze

-0.26

 typename

-0.26

 ingen

-0.25

POSITIVE LOGITS

ç«łç¨ĭ

0.26

 Institutional

0.25

PageIndex

0.25

NFL

0.25

 locker

0.25

.ToLower

0.24

_THROW

0.23

 Locker

0.23

æĥ³æĥ³

0.23

é¢ł

0.23

Activations Density 1.036%

No Known Activations

This feature has no known activations.