INDEX

Explanations

Dating systems

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

 Rosenberg

-0.27

åħ¥èĤ¡

-0.26

å²Ĳ

-0.25

 Karn

-0.25

 setuptools

-0.25

merican

-0.24

ç«ĭæĸ¹

-0.24

 mell

-0.24

Ð´Ð°ÑĢ

-0.23

won

-0.23

POSITIVE LOGITS

å°ıçĻ½

0.26

è®³

0.25

think

0.25

LER

0.24

lish

0.24

 Ð²ÑĭÐ±ÑĢ

0.24

host

0.23

 costing

0.23

Ð³ÑĢÐ°Ð½Ð¸Ñĩ

0.23

 footing

0.23

Activations Density 0.001%

Dating systems

No Comments

No Known Activations