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

erval

-0.26

ä¸Ģæī¹

-0.26

 Bloom

-0.25

chl

-0.24

 ctrl

-0.24

å±ħå®¤

-0.24

ILLE

-0.24

å°ıæĹ¶åīį

-0.24

.va

-0.23

tag

-0.23

POSITIVE LOGITS

pline

0.29

anke

0.28

oline

0.27

tÃ©

0.27

addle

0.26

ovsky

0.26

wise

0.25

aine

0.24

 Irvine

0.24

åĳĹ

0.24

Activations Density 0.000%

No Known Activations

This feature has no known activations.