INDEX

Explanations

companies/organizations

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

çªģ

-0.31

 STOCK

-0.30

gst

-0.28

etta

-0.27

uent

-0.27

é©±

-0.26

 Banc

-0.26

ê¸ī

-0.26

uenta

-0.25

ÐĲÐŀ

-0.25

POSITIVE LOGITS

æĬĦ

0.27

.Ed

0.26

andler

0.26

 Scha

0.26

ç½Ĳ

0.25

èĨı

0.24

orus

0.24

åģıåģı

0.24

holes

0.24

ANEL

0.24

Activations Density 0.001%

companies/organizations

No Comments

No Known Activations