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

ãģĦãģĨ

-0.27

mere

-0.26

 doGet

-0.25

ä¸°æ»¡

-0.24

èģ

-0.23

ä¹ĭä½Ļ

-0.23

éĢµ

-0.23

 lighter

-0.23

<?↵

-0.23

-mini

-0.23

POSITIVE LOGITS

Constraints

0.29

esp

0.26

resse

0.26

 Ð¿ÑĢÐ¾Ð³

0.26

 Constant

0.25

uste

0.25

åı¤èĢģçļĦ

0.24

buc

0.24

eut

0.24

 snapped

0.23

Activations Density 0.012%

No Known Activations

This feature has no known activations.