INDEX

Explanations

technical/code related texts

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç«ĭ

-0.27

 serialVersionUID

-0.27

umps

-0.26

arhus

-0.26

NIL

-0.25

pering

-0.25

enkins

-0.24

-comm

-0.24

 unsus

-0.24

èĵ

-0.24

POSITIVE LOGITS

åĮħè¢±

0.29

balanced

0.26

asInstanceOf

0.26

paged

0.25

ãĤ¨ãĥ³

0.24

çĥ«

0.24

 formatter

0.23

 architecture

0.23

æĢ¥æĢ§

0.23

åħļæĶ¿

0.23

Activations Density 0.006%

technical/code related texts

No Comments

No Known Activations