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

ople

-0.29

isode

-0.27

orph

-0.26

Ba

-0.26

peon

-0.25

ØªÙĤ

-0.25

æ²ħ

-0.25

æĿĸ

-0.24

templates

-0.24

 Paula

-0.23

POSITIVE LOGITS

#__

0.29

[assembly

0.28

 detriment

0.25

åı¯æĥ³

0.25

ç³»åĪĹ

0.25

è¿ĺè®°å¾Ĺ

0.24

 cardinal

0.24

 series

0.24

 negoci

0.24

ä¾ĿçĦ¶æĺ¯

0.23

Activations Density 0.001%

No Known Activations

This feature has no known activations.