INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_18.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.18.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

FINITE

-0.31

Ð²ÐµÑĤ

-0.28

 MATCH

-0.28

adero

-0.28

æĹłéĻĲ

-0.26

 investor

-0.26

çŁ¥æĥħ

-0.25

.WinForms

-0.24

 sale

-0.24

 TRADE

-0.24

POSITIVE LOGITS

esh

0.27

åľľ

0.26

 optional

0.26

BTN

0.25

idden

0.25

pac

0.25

achines

0.24

åİ»åĵªåĦ¿

0.24

æĪĲåĬŁçļĦ

0.24

Activations Density 0.958%

No Known Activations

This feature has no known activations.