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

ä¸ĢæŃ¥

-0.26

ç§°

-0.26

.nio

-0.25

 Hindus

-0.25

ä¸Ģæ¬¡

-0.24

åıĹ

-0.24

 Rath

-0.24

-collar

-0.23

 bers

-0.23

 Head

-0.23

POSITIVE LOGITS

 incons

0.27

syn

0.25

 visualization

0.25

 cabinets

0.25

peri

0.24

Syn

0.24

opause

0.23

çļĦå¤§

0.23

Twe

0.23

_syn

0.23

Activations Density 0.006%

No Known Activations

This feature has no known activations.