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

Tay

-0.28

åŁºæķ°

-0.27

Builders

-0.24

TECTED

-0.24

constructor

-0.24

åī½

-0.24

Constructor

-0.23

Ð¾ÑĢÐ¾

-0.23

usta

-0.23

éĥ½éĿŀå¸¸

-0.23

POSITIVE LOGITS

èģĶæĥ³

0.28

OTA

0.27

ENE

0.27

èĮĥåĽ´åĨħ

0.27

ç¤¼

0.26

ç¬¬ä¸īä»£

0.25

æľªæĿ¥

0.25

inium

0.25

strup

0.25

INK

0.24

Activations Density 0.003%

No Known Activations

This feature has no known activations.