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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 advance

-0.35

 Advance

-0.32

 sweet

-0.29

 advanced

-0.29

Advance

-0.27

ged

-0.27

------------------------------------------------

-0.26

...

-0.26

 suff

-0.26

owell

-0.25

POSITIVE LOGITS

ulet

0.30

itere

0.28

æľīåĬ©

0.27

å¾Īå¿«å°±

0.27

PLETED

0.26

 REFER

0.26

iterated

0.26

kest

0.26

ä¸Ģéĺµ

0.25

IDD

0.25

Activations Density 0.009%

No Known Activations

This feature has no known activations.