INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

/epl

-0.27

ula

-0.27

equ

-0.25

ective

-0.25

çºª

-0.25

íĤ¤

-0.25

éĴĹ

-0.24

uckles

-0.24

-character

-0.24

éŀŃ

-0.24

POSITIVE LOGITS

ARS

0.26

lien

0.25

SCAN

0.24

æīįè¡Į

0.24

ars

0.24

:initComponents

0.24

 anyhow

0.24

ommen

0.23

 Weekend

0.23

Äħd

0.23

Activations Density 4.029%

No Known Activations

This feature has no known activations.