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

ansom

-0.29

feit

-0.29

 near

-0.28

 revis

-0.28

çĶ·ç¥ŀ

-0.26

èĽĻ

-0.26

åĿļå®ļä¸įç§»

-0.26

 drops

-0.25

near

-0.25

 Ø§ÙĦÙħØµ

-0.24

POSITIVE LOGITS

[prop

0.26

ewire

0.25

riendly

0.25

 Current

0.25

asia

0.24

 gastro

0.24

adel

0.23

çĥ¯

0.23

benh

0.23

 ..."

0.23

Activations Density 0.012%

No Known Activations

This feature has no known activations.