INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

izen

-0.25

 rational

-0.24

è¿ĻåĲį

-0.24

 monkey

-0.24

 hooks

-0.24

 Lance

-0.23

 prepared

-0.23

hed

-0.23

 consequence

-0.23

 Huffman

-0.23

POSITIVE LOGITS

å¹¶éĿŀ

0.29

æĴŀ

0.27

udios

0.26

tings

0.25

/tags

0.25

Meanwhile

0.24

ä¸Ģç»ı

0.24

ulpt

0.24

ATAB

0.23

tein

0.23

Activations Density 0.009%

No Known Activations

This feature has no known activations.