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

uft

-0.27

åľ°ä¸Ń

-0.26

çļĦèĢģ

-0.26

çĪ¨

-0.26

 Ð³ÑĢÐ°Ð¶Ð´Ð°Ð½

-0.26

æľį

-0.25

platz

-0.25

 partisan

-0.25

 repos

-0.25

-ticket

-0.25

POSITIVE LOGITS

çıı

0.28

å¤«å¦ĩ

0.28

åı¹

0.27

 illustration

0.26

igmoid

0.26

è¢«æ·ĺæ±°

0.26

 geometry

0.26

.ads

0.25

opaque

0.25

 pains

0.25

Activations Density 0.412%

No Known Activations

This feature has no known activations.