INDEX

Explanations

Marshall

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

ç½ĳè®¯

-0.29

loys

-0.28

 Location

-0.27

Ð»Ð°Ñģ

-0.26

perator

-0.26

Location

-0.25

iterated

-0.25

location

-0.25

trÃ©

-0.24

unc

-0.24

POSITIVE LOGITS

agram

0.31

æłĪ

0.27

-syntax

0.26

ETH

0.25

_MAC

0.25

-rest

0.24

æĮīä¸ĭ

0.24

-ring

0.24

asure

0.24

yr

0.24

Activations Density 0.783%

Marshall

No Comments

No Known Activations