INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

uten

-0.27

**↵

-0.27

èĩĤ

-0.26

è´¢çī©

-0.25

æ³¡

-0.25

**č↵

-0.25

åĪ©

-0.25

æıĲåĩºçļĦ

-0.25

{}".

-0.24

ayah

-0.24

POSITIVE LOGITS

ç»¼åĲĪä½ĵ

0.28

æĿĳéķĩ

0.27

BITS

0.24

ä¸įçĶĺ

0.24

åŁİä¹¡å±ħæ°ĳ

0.24

 Linden

0.24

æľīä¸Ģç§į

0.24

.AddListener

0.24

rum

0.23

åºĬåŀ«

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.