INDEX

Explanations

Locations/Organizations/Proper Nouns

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

tract

-0.28

ä¸»ä¹īæĢĿæĥ³

-0.28

errat

-0.27

sWith

-0.26

MCS

-0.25

 suff

-0.24

.Accept

-0.24

nection

-0.23

GM

-0.23

 baja

-0.23

POSITIVE LOGITS

ĪæĿĥ

0.29

estimate

0.27

again

0.26

å¼º

0.26

.nz

0.26

 bidding

0.26

 Edinburgh

0.25

Ð°ÑĪ

0.25

inspace

0.24

æĦıåĲĳ

0.24

Activations Density 0.000%

Locations/Organizations/Proper Nouns

No Comments

No Known Activations