INDEX

Explanations

Demographic groups

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

æŁĲç§į

-0.29

ç»ıåħ¸çļĦ

-0.29

åĲĪéĢĤçļĦ

-0.28

åĵªä¸ª

-0.27

çº¢èī²

-0.27

 Concrete

-0.26

Ð½ÑĭÐ¹

-0.25

WX

-0.25

Acc

-0.25

Un

-0.24

POSITIVE LOGITS

 adults

0.31

 citizens

0.29

 youngsters

0.28

ä¼ģä¸ļæıĲä¾Ľ

0.28

:href

0.28

 ventures

0.27

èģĮä¸ļçĶŁæ¶¯

0.27

 youths

0.26

orph

0.26

rians

0.26

Activations Density 0.007%

Demographic groups

No Comments

No Known Activations