INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¸ĭæ»ĳ

-0.28

clud

-0.27

/svg

-0.25

uron

-0.25

exual

-0.24

tty

-0.24

 Glenn

-0.24

äºĨå¾Īä¹ħ

-0.24

nest

-0.23

 háºŃu

-0.23

POSITIVE LOGITS

èĥĮ

0.30

-known

0.26

åħħåĪĨ

0.25

 seminar

0.25

ISE

0.25

shade

0.24

é»ĺ

0.24

ä¸īæĿ¡

0.24

 Bale

0.24

isme

0.24

Activations Density 0.039%

No Known Activations

This feature has no known activations.