INDEX

Explanations

exchange or transaction

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å±¥

-0.28

æīĢä»¥ä»ĸ

-0.26

lld

-0.26

 Floating

-0.24

atars

-0.24

å§ĵ

-0.24

ãĥ¥ãĥ¼

-0.24

 Incident

-0.23

logical

-0.23

çļĦæĢ§æł¼

-0.23

POSITIVE LOGITS

åĩºåĵģ

0.28

çĤ¹åįĬ

0.26

ervas

0.25

cerpt

0.25

åĩĨ

0.25

åıĮè¾¹

0.25

 american

0.25

pac

0.25

oday

0.25

ä¾Ŀèµĸ

0.24

Activations Density 0.003%

exchange or transaction

No Comments

No Known Activations