INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

quence

-0.32

rez

-0.29

éĹ®é¢ĺæĺ¯

-0.27

uz

-0.26

zan

-0.26

Æ°á»Ŀ

-0.25

hob

-0.25

ãĥĻ

-0.25

pak

-0.25

ä¹¾åĿ¤

-0.25

POSITIVE LOGITS

çŁ¥å·±

0.28

è§Ĩçº¿

0.25

éŁ³åĵį

0.25

ViewChild

0.25

 Macron

0.25

 clouds

0.25

ajÄħce

0.25

morgan

0.25

.parseFloat

0.24

 âĨĴ↵↵

0.24

Activations Density 0.436%

No Known Activations

This feature has no known activations.