INDEX

Explanations

likely

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

ä¸ĩåĪĨ

-0.26

 Fowler

-0.26

['__

-0.25

 Reform

-0.25

bound

-0.25

çļĦä¿¡ä»»

-0.25

ä½Ľ

-0.24

 screw

-0.24

çļĦç»ıéªĮ

-0.24

 opportunity

-0.24

POSITIVE LOGITS

 onCancelled

0.27

åĮ»åĬ¡äººåĳĺ

0.27

å¤§å¤«

0.26

earch

0.26

 Mater

0.25

æŃ¦èŃ¦

0.25

_ATTRIBUTES

0.25

éº¦åħĭ

0.24

åĮ»æĬ¤äººåĳĺ

0.24

 drank

0.24

Activations Density 0.006%

likely

No Comments

No Known Activations