INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¹ŀ

-0.29

å®¿è¿ģ

-0.27

åĲĪèµĦ

-0.27

spir

-0.27

č↵↵

-0.27

MZ

-0.25

æ¸ħæ¾Ī

-0.25

éķ¶åµĮ

-0.24

DETAIL

-0.24

tere

-0.24

POSITIVE LOGITS

autop

0.27

 Gathering

0.27

ank

0.27

 nominations

0.26

 downstream

0.26

ank

0.25

ç¨¿

0.25

è¿ľç¨ĭ

0.25

Him

0.25

hub

0.24

Activations Density 0.109%

No Known Activations

This feature has no known activations.