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

ãĥ¬ãĤ¹

-0.27

isu

-0.25

noon

-0.25

_te

-0.25

appendTo

-0.24

Ãło

-0.24

WR

-0.24

¢åįķ

-0.23

æĽ´å¤ļä¿¡æģ¯

-0.23

 revolving

-0.23

POSITIVE LOGITS

achs

0.27

å½Ĵ

0.25

pike

0.25

 Bender

0.24

rock

0.24

 pigment

0.24

à¹Ĥà¸Ĭà¸Ħ

0.24

ä¸»åĬŀ

0.24

uch

0.24

à¹Īà¸²à¸§

0.23

Activations Density 0.002%

No Known Activations

This feature has no known activations.