INDEX

Explanations

delivering

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

urtle

-0.27

åĤĳ

-0.25

 Escorts

-0.25

éĤ´

-0.25

 fleets

-0.24

-summary

-0.24

HttpException

-0.24

 defin

-0.23

 Cooperative

-0.23

ä»£çĲĨ

-0.23

POSITIVE LOGITS

 splits

0.29

 split

0.28

 Split

0.27

 splitted

0.27

 splitting

0.26

 Universal

0.26

 Parent

0.26

eso

0.25

_split

0.25

.newInstance

0.25

Activations Density 0.001%

delivering

No Comments

No Known Activations