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

berger

-0.26

bens

-0.25

 Presented

-0.24

fle

-0.24

æĹ¥äº§

-0.23

//----------------------------------------------------------------------------------------------------------------

-0.22

 Leonard

-0.22

 must

-0.22

 bott

-0.22

POSITIVE LOGITS

astr

0.31

Ã¶m

0.27

artment

0.26

ÐµÑģÑĤÐ²

0.26

IPA

0.25

ç´«å¤ĸ

0.25

+)/

0.24

-chief

0.24

ToLocal

0.24

ä¸ĢåľĪ

0.24

Activations Density 0.011%

No Known Activations

This feature has no known activations.