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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

éĢĲ

-0.28

 Contracts

-0.27

ÅĽnie

-0.26

ÅĽcie

-0.25

æĪ³

-0.24

 Cursors

-0.23

reste

-0.23

è¦ĨçĽĸéĿ¢

-0.23

atem

-0.23

 SIDE

-0.23

POSITIVE LOGITS

kÃ¶

0.28

obb

0.25

 comps

0.25

ooks

0.25

åĺī

0.24

ms

0.24

rep

0.24

rud

0.24

Anchor

0.24

ä¸ĽæŀĹ

0.24

Activations Density 0.002%

No Known Activations

This feature has no known activations.