INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_24.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.24.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

icher

-0.29

 Bout

-0.27

iche

-0.26

icum

-0.26

éĽħ

-0.25

IJ

-0.25

ãĥªãĤ¢

-0.24

çļĦä¿¡ä»»

-0.24

ich

-0.24

|RF

-0.24

POSITIVE LOGITS

ewith

0.27

Ä±yla

0.26

 Blood

0.26

Min

0.24

è¾ĺ

0.24

 Host

0.24

è¡Ģ

0.24

odable

0.23

Blood

0.23

 bullet

0.23

Activations Density 0.205%

No Known Activations

This feature has no known activations.