INDEX

Explanations

in

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_2.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.2.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Vs

-0.27

éĹ

-0.27

OPSIS

-0.27

åħĪè¿Ľ

-0.27

 gran

-0.25

à¹Ģà¸¥à¸¢

-0.25

è±¡

-0.25

hir

-0.24

bind

-0.24

vang

-0.24

POSITIVE LOGITS

åıĹä¸įäºĨ

0.26

 Laden

0.26

.createComponent

0.25

createForm

0.25

 Alloy

0.25

ascar

0.25

 lawful

0.24

 mesmer

0.24

 REPRESENT

0.24

OUSE

0.24

Activations Density 40.881%

in

No Comments

No Known Activations