INDEX

Explanations

different types of documents

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

mercial

-0.26

ADI

-0.26

adi

-0.26

pter

-0.25

çŁĽ

-0.25

 quÃł

-0.25

 Economist

-0.24

 moderation

-0.24

uyÃªn

-0.24

 unfit

-0.24

POSITIVE LOGITS

æłĩ

0.28

è¹ī

0.26

requent

0.25

antt

0.25

usters

0.24

åĬ³

0.24

ÐºÑĢÐ¾Ð²

0.23

çľ¼çļ®

0.23

anco

0.23

reff

0.23

Activations Density 0.001%

different types of documents

No Comments

No Known Activations