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

çĶŁæ´»çļĦ

-0.27

schlÃ¤

-0.26

çħ§

-0.25

zenie

-0.25

æī¬

-0.24

æĥ³

-0.23

—

-0.23

åıį

-0.23

 Impro

-0.23

 Nass

-0.23

POSITIVE LOGITS

 upro

0.28

ign

0.26

 revenge

0.25

phis

0.25

chan

0.25

/TR

0.24

ument

0.24

 portfolios

0.24

ounder

0.24

igner

0.24

Activations Density 0.001%

No Known Activations

This feature has no known activations.