INDEX

Explanations

No Explanations Found

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.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

station

-0.27

 instructor

-0.26

çĭ¼

-0.25

ç«Ļ

-0.25

TECT

-0.25

ÅĤu

-0.25

 station

-0.24

ä¸Ĭåĳ¨

-0.24

sey

-0.23

 preserved

-0.23

POSITIVE LOGITS

.Transactional

0.25

encing

0.25

 spoilers

0.24

éĺĻ

0.24

 orthodox

0.23

 Boyle

0.23

åĮĹæĸĹ

0.23

oup

0.23

_mask

0.23

 masks

0.23

Activations Density 0.007%

No Comments

No Known Activations