INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç®¡å±Ģ

-0.28

pole

-0.25

å¹²æī°

-0.25

 bake

-0.25

empre

-0.25

çļĦä¿¡æģ¯

-0.24

çļĦçİ°è±¡

-0.24

TextNode

-0.23

uctive

-0.23

ç¢Į

-0.23

POSITIVE LOGITS

elay

0.26

_mx

0.25

band

0.24

 Band

0.24

Band

0.23

.sw

0.23

iband

0.23

pe

0.23

åı¯ä»¥è¯´

0.23

_band

0.23

Activations Density 0.066%

No Known Activations

This feature has no known activations.