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

ag

-0.26

 miniature

-0.26

sc

-0.25

ipp

-0.24

 SHOULD

-0.24

çľģéĴ±

-0.23

 prolong

-0.23

 part

-0.23

mn

-0.23

tom

-0.22

POSITIVE LOGITS

å²Ĺ

0.26

rxjs

0.25

_pitch

0.24

TextEdit

0.24

.pitch

0.23

ennes

0.23

icias

0.23

å½±éŁ³

0.23

pitch

0.23

 Truck

0.23

Activations Density 1.191%

No Known Activations

This feature has no known activations.