INDEX

Explanations

title or copyright

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_22.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.22.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Chevron

-0.26

çĪ¨

-0.25

æĸŃ

-0.24

overn

-0.24

 cave

-0.24

ologically

-0.23

ologÃŃa

-0.23

 BaseEntity

-0.23

æ±°

-0.23

 dismiss

-0.23

POSITIVE LOGITS

è¡ĮåĪĹ

0.29

Ð°ÑĢÐ°Ð¼

0.29

IOS

0.27

åı³æīĭ

0.26

å¯ĨéĽĨ

0.26

æĿ¥èĩª

0.26

IMS

0.25

aram

0.24

[$_

0.24

rin

0.23

Activations Density 0.008%

title or copyright

No Comments

No Known Activations