INDEX

Explanations

Technical/Formal documents

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

 involuntary

-0.26

ç»¼

-0.26

icos

-0.25

 fundamentally

-0.25

 LATIN

-0.25

ìĭł

-0.24

orate

-0.24

sog

-0.24

IPH

-0.24

åĪĨéĴŁå·¦åı³

-0.24

POSITIVE LOGITS

æ²³

0.28

ernal

0.26

utra

0.25

graph

0.25

River

0.25

 wheel

0.25

 graph

0.24

 Graph

0.24

Numeric

0.24

ÏĮ

0.24

Activations Density 0.000%

Technical/Formal documents

No Comments

No Known Activations