INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_20.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.20.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ometric

-0.27

plet

-0.27

_uv

-0.26

åħĳ

-0.26

tem

-0.26

quo

-0.25

bic

-0.25

 Easter

-0.25

vez

-0.24

.GetCurrent

-0.24

POSITIVE LOGITS

GCC

0.27

caret

0.26

gcc

0.26

èģĭ

0.25

ãĥĭãĤ¢

0.25

/gcc

0.25

(or

0.24

æī§æ³ķ

0.24

GCC

0.24

pill

0.24

Activations Density 49.039%

No Known Activations

This feature has no known activations.