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

å¦Ĩ

-0.34

æį·

-0.29

.syntax

-0.28

íį¼

-0.27

syntax

-0.27

æ²¡åħ³ç³»

-0.27

.âĢ¦↵↵

-0.26

isure

-0.26

ä¸įåľ¨ä¹İ

-0.25

hsi

-0.25

POSITIVE LOGITS

etics

0.30

archs

0.29

åİŁåĽłä¹ĭä¸Ģ

0.27

dev

0.26

 Ledger

0.26

-spec

0.26

etro

0.26

arts

0.25

edImage

0.25

eters

0.25

Activations Density 0.000%

No Known Activations

This feature has no known activations.