INDEX

Explanations

Informal text snippets

np_max-act · gemini-2.0-flash

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

åºŀå¤§çļĦ

-0.29

	union

-0.28

éĿŀå¸¸å¤ļçļĦ

-0.27

_asm

-0.27

stile

-0.27

rame

-0.26

essional

-0.26

 adamant

-0.25

 Usually

-0.24

arching

-0.24

POSITIVE LOGITS

ä¸Ģä¸ĭ

0.81

äºĽ

0.77

 some

0.69

ä¸ĢäºĽ

0.66

ä¸ĢçĤ¹

0.61

some

0.56

 Some

0.56

Some

0.55

äºĨè§£ä¸Ģä¸ĭ

0.52

çľĭä¸Ģä¸ĭ

0.51

Activations Density 0.013%

Informal text snippets

No Comments

No Known Activations