INDEX

Explanations

Code/Documentation

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ignet

-0.31

deaux

-0.28

eced

-0.26

æľīåĬ©äºİ

-0.25

rade

-0.25

iske

-0.25

 prime

-0.25

.Multi

-0.24

sent

-0.24

 sent

-0.24

POSITIVE LOGITS

ambi

0.26

åĿļå®ļä¸įç§»

0.24

UnderTest

0.24

æĸĹ

0.23

èĦ²

0.23

å®¾

0.23

Fra

0.23

ourage

0.23

è½¬è½½è¯·

0.23

 ----------------------------------------------------------------------------------------------------------------

0.23

Activations Density 0.001%

Code/Documentation

No Comments

No Known Activations