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

çº¸ä¸Ĭ

-0.30

èĥ¸åīį

-0.27

ç¿¼

-0.26

czy

-0.25

å®īåİ¿

-0.24

chl

-0.24

Ð³Ð»Ð°Ð²

-0.24

nish

-0.24

éħ¹

-0.24

isel

-0.24

POSITIVE LOGITS

ste

0.32

 Stein

0.29

ste

0.28

unt

0.28

imately

0.27

åĩĮ

0.26

-ste

0.26

 accumulated

0.26

è¿½

0.25

ãĤīãģĦ

0.25

Activations Density 0.038%

No Known Activations

This feature has no known activations.