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

Giz

-0.32

 truth

-0.27

åįĩ

-0.26

-opacity

-0.26

exao

-0.26

alty

-0.24

 testName

-0.24

çŁ¿åĮº

-0.24

åĳ½

-0.24

POSITIVE LOGITS

agra

0.28

éº½

0.26

-Year

0.26

ç¨³å®ļçļĦ

0.24

éļĪ

0.24

èĨ³

0.23

leston

0.23

.Tick

0.23

æ°ĳæĹı

0.23

 petitioner

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.