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

 alloc

-0.29

å¹´åĨħ

-0.28

Alloc

-0.27

wig

-0.26

 allocator

-0.24

çªĸ

-0.24

åħ¬çĶ¨

-0.24

 piss

-0.24

ALLOC

-0.23

 mutil

-0.23

POSITIVE LOGITS

rous

0.30

iche

0.25

 UserType

0.24

angu

0.24

æĸ¹

0.24

 FieldType

0.24

inz

0.24

ize

0.23

 -----------------------------------------------------------------------------↵

0.23

èį¥

0.23

Activations Density 0.004%

No Known Activations

This feature has no known activations.