INDEX

Explanations

Questions

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

calar

-0.30

]+\

-0.27

ç¨¿ä»¶

-0.26

ä»Ģä¹Īäºĭæĥħ

-0.26

 Hubb

-0.26

sav

-0.25

reater

-0.24

 BaseType

-0.24

äº¤ç»ĩ

-0.24

å®ŀæĥł

-0.23

POSITIVE LOGITS

 defence

0.28

åĲįä¸º

0.25

defense

0.25

che

0.25

ACHED

0.25

 educ

0.24

åĲĳ

0.24

education

0.24

 herself

0.24

 defense

0.24

Activations Density 0.002%

Questions

No Comments

No Known Activations