INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

mute

-0.26

ÑĢÐ°Ð³

-0.25

éĺĻ

-0.25

æī§åĭ¤

-0.25

æĮ¡ä½ı

-0.25

SenderId

-0.24

é©¾çħ§

-0.24

cken

-0.23

èĬ®

-0.23

aug

-0.23

POSITIVE LOGITS

lessly

0.28

AIN

0.25

 Highlands

0.24

spr

0.24

æĹłå½¢

0.24

 median

0.24

 poem

0.24

branch

0.23

ern

0.23

 there

0.23

Activations Density 0.000%

No Known Activations

This feature has no known activations.