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

ç¾

-0.28

refs

-0.26

æ¤Ĵ

-0.25

éĥ½æ²¡

-0.25

éĥ½ä¸į

-0.25

OOT

-0.24

æįİ

-0.24

 Appet

-0.24

æĭĽ

-0.24

è£

-0.23

POSITIVE LOGITS

 Freed

0.26

dings

0.25

rÃ´

0.24

 Vision

0.24

yst

0.24

radi

0.23

edback

0.23

 Dragons

0.23

æīĢè¯´çļĦ

0.23

vision

0.23

Activations Density 0.025%

No Known Activations

This feature has no known activations.