INDEX

Explanations

code/programming

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æĸĹ

-0.27

çĽŁ

-0.27

.isPresent

-0.25

.preventDefault

-0.24

ÚĪ

-0.24

.djang

-0.23

 Sample

-0.23

ResultsController

-0.23

åħ¬æŃ£

-0.23

Sample

-0.23

POSITIVE LOGITS

kers

0.28

è¿½è¸ª

0.27

_gps

0.26

\xff

0.26

èµ¤

0.25

agma

0.25

skins

0.24

xls

0.24

skin

0.24

offs

0.24

Activations Density 0.008%

code/programming

No Comments

No Known Activations