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

Inc

-0.28

æĸ¹æ¡Ī

-0.27

ancies

-0.25

å¸Įå°Ķ

-0.25

bei

-0.25

å»ī

-0.24

ugi

-0.24

IMAL

-0.24

esch

-0.23

ATCH

-0.23

POSITIVE LOGITS

 office

0.28

orges

0.27

Kent

0.27

opot

0.27

-office

0.26

Bat

0.25

 absorption

0.25

èĲ¥éĢłèī¯å¥½

0.25

Raster

0.24

å·©

0.24

Activations Density 41.239%

No Known Activations

This feature has no known activations.