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

-inv

-0.27

ARIANT

-0.26

å·¥åľ°

-0.26

 brid

-0.25

FILENAME

-0.25

lder

-0.25

OCI

-0.25

ä¼ļéķ¿

-0.25

 convinc

-0.24

acer

-0.24

POSITIVE LOGITS

çĵ£

0.28

æ¼ıæ°´

0.27

 fins

0.27

LayoutPanel

0.25

 Rights

0.25

 Listen

0.25

Rif

0.25

.refs

0.25

åĲ¬è¯¾

0.25

 Chap

0.24

Activations Density 0.067%

No Known Activations

This feature has no known activations.