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

Ø±Ø£

-0.28

 pellets

-0.28

zos

-0.26

embers

-0.26

 pellet

-0.26

alien

-0.25

igrated

-0.25

enu

-0.25

lien

-0.25

çĥŁ

-0.24

POSITIVE LOGITS

ardo

0.30

çĽĽ

0.25

Ð¾Ð²Ð°ÑĢ

0.24

å°¾å·´

0.24

sid

0.24

äººå®¶

0.24

ORK

0.23

èĦ¾æ°Ķ

0.23

æıĲæĭĶ

0.23

$path

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.