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

çĪ¶åŃĲ

-0.27

 Futures

-0.25

æ»Ł

-0.25

æħ¢æħ¢

-0.25

 Presents

-0.24

æŃ£å½ĵ

-0.24

 IHttp

-0.24

è´°

-0.24

äº¤éĢļ

-0.24

Invariant

-0.23

POSITIVE LOGITS

ä»ħä»£è¡¨

0.28

autoload

0.28

ire

0.27

Sw

0.27

tat

0.27

table

0.26

 reference

0.25

reference

0.25

laden

0.25

prises

0.25

Activations Density 0.008%

No Known Activations

This feature has no known activations.