INDEX

Explanations

educational, informational, only

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

è´

-0.30

erala

-0.28

 Liberties

-0.27

DET

-0.27

 devil

-0.26

DETAIL

-0.25

 Ð²ÑĭÐ±ÑĢ

-0.25

rowData

-0.25

_traits

-0.25

,url

-0.25

POSITIVE LOGITS

SHIP

0.31

wn

0.26

Ð°Ñħ

0.25

 mans

0.25

grÃ¶ÃŁe

0.24

~/

0.24

leon

0.24

æĬķæľº

0.24

stre

0.24

æĶ»åħ³

0.24

Activations Density 0.002%

educational, informational, only

No Comments

No Known Activations