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

ati

-0.32

idis

-0.28

 Comm

-0.27

atie

-0.26

&t

-0.25

osto

-0.25

fos

-0.25

pr

-0.24

arya

-0.24

(sequence

-0.24

POSITIVE LOGITS

æĹłç§ģ

0.29

italic

0.29

PathVariable

0.28

 inev

0.27

Rae

0.26

çļĦæĥħ

0.26

obili

0.26

æ´ŀ

0.26

-Ray

0.26

æĹłæĦı

0.26

Activations Density 0.047%

No Known Activations

This feature has no known activations.