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

ä¸¥

-0.31

ä¸įä½ı

-0.27

 stamped

-0.25

æİĮå£°

-0.25

 sampling

-0.25

å±¥èģĮ

-0.25

tre

-0.24

 táº¥m

-0.24

çº¢æĹĹ

-0.24

çļĦå£°éŁ³

-0.24

POSITIVE LOGITS

imb

0.29

ivities

0.27

ivist

0.26

ivant

0.26

nell

0.25

rÃ¡

0.25

etics

0.24

ToBounds

0.24

atal

0.24

ãĥĭãĥ¥ãĥ¼ãĤ¹

0.24

Activations Density 14.381%

No Known Activations

This feature has no known activations.