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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 modelos

-0.31

ailer

-0.29

ATAL

-0.27

plets

-0.27

çº¢æĺŁ

-0.26

ourcem

-0.26

ledon

-0.25

yme

-0.25

 daycare

-0.25

ä¼ģä¸ļåĴĮ

-0.25

POSITIVE LOGITS

equ

0.32

CM

0.30

0.29

CM

0.29

 stiffness

0.28

 Ð¾ÑĦÐ¾ÑĢÐ¼Ð»ÐµÐ½

0.28

0.27

æ¶İ

0.27

0.26

Activations Density 0.009%

No Known Activations

This feature has no known activations.