INDEX

Explanations

to

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

 sÃ³

-0.25

æĮĩç¤º

-0.25

 hinted

-0.25

ë§Īëĭ¤

-0.24

 newRow

-0.23

 cáº£

-0.23

ç¥ģ

-0.23

-INF

-0.23

amina

-0.23

 invited

-0.23

POSITIVE LOGITS

åĴİ

0.29

aland

0.26

 maxim

0.25

yyn

0.25

 Calories

0.25

burg

0.24

InstanceState

0.24

çĲĨçĶ±

0.24

è¿Ļä»¶äºĭæĥħ

0.24

çĹĩ

0.23

Activations Density 0.001%

to

No Comments

No Known Activations