INDEX

Explanations

Subtraction symbols

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.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

_SAFE

-0.27

å±£

-0.26

-mf

-0.26

 joking

-0.25

ORED

-0.24

ukan

-0.24

åī¯æķĻæİĪ

-0.23

ç½¨

-0.23

 Chief

-0.23

_chr

-0.23

POSITIVE LOGITS

0.47

åĩı

0.42

0.41

 minus

0.39

åĬł

0.36

 âĪĴ

0.36

minus

0.35

âĪĴ

0.35

-minus

0.33

0.31

Activations Density 0.019%

Subtraction symbols

No Comments

No Known Activations