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

Negative Logits

<article

-0.29

 Wonderland

-0.27

éģ½

-0.25

Ð²ÑıÐ·

-0.25

RESS

-0.24

 daytime

-0.24

å¼µè²¼

-0.24

Manifest

-0.24

 getopt

-0.24

ä»ħä»£è¡¨

-0.24

POSITIVE LOGITS

idal

0.27

çĶ¨éĢĶ

0.25

çĮİ

0.25

çķ´

0.25

èħ¹

0.24

 dope

0.24

ulated

0.23

iren

0.23

itic

0.23

é«Ĥ

0.23

Activations Density 1.962%

No Known Activations

This feature has no known activations.