INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Sunshine

-0.28

ertype

-0.25

anship

-0.25

HDR

-0.25

 sunshine

-0.24

mdir

-0.24

åĪİ

-0.24

ç³ľ

-0.24

ularity

-0.24

 Vand

-0.24

POSITIVE LOGITS

XS

0.28

 query

0.26

axed

0.25

ava

0.25

ç¿Ķ

0.25

 course

0.25

å®Ī

0.24

alm

0.24

çĲĥ

0.24

 querying

0.24

Activations Density 0.393%

No Known Activations

This feature has no known activations.