INDEX

Explanations

identifiers

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

posal

-0.31

thal

-0.25

æ¿Ģç´ł

-0.25

uhan

-0.24

 adaptations

-0.24

 Russians

-0.24

DOCTYPE

-0.23

æĪĳæ²¡æľī

-0.23

è½®èĥİ

-0.23

åºĶæĶ¶è´¦æ¬¾

-0.23

POSITIVE LOGITS

æ¡¢

0.31

 Lunch

0.29

:hidden

0.28

.tem

0.26

åĢį

0.26

:Object

0.26

åŁ¹

0.25

lod

0.24

ven

0.24

 frameworks

0.24

Activations Density 0.002%

identifiers

No Comments

No Known Activations