Neuron Explorer

Qwen3-0.6B

"so" opening a purpose clause

A neuron in layer 20 of Qwen3-0.6B. Its strongest snippets are very consistent: they mostly peak on the same token. It is featured, so it has steering outputs.

What this neuron does

This neuron fires on the word "so" when it introduces a purpose, as in "so that" or "so as to". Turning it up made the model repeat "that as as as", and the negative side is weak and mostly on "make" in phrases like "built to make".

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).

Fires most on

The text windows where this neuron's activation was highest. Amber marks positive activation; the outlined token is the peak. Hover a token for its strength.

  1. #1 peak

    adequacy of reservation for them. The major hurdle for the effective dispensation of social justice is the lack of data on sectoral population, and their due representation so far.⏎The identity of caste degradation is permeated in the socio, economic and

  2. #2 peak

    treats of the best means of directing school affairs so as to secure efficiency. It includes not only school economy, but also school discipline

  3. #3 peak

    diseases to a certain level.⏎Microbial science is the detailed study of microorganisms that are tiny and it is important to understand the performance of every microorganism so that better understanding can be generated towards the living bodies. Microbial sciences help in

  4. #4 peak

    the building. For example, if your building is minimalist concept, then create a park with the same concept. Garden design should fit with the concept of the building so that it becomes a harmonious unity⏎Well, the next step is clean the

  5. #5 peak

    These are the commands, decrees and laws the Lord your God directed me to teach you to observe in the land that you are crossing the Jordan to possess, so that you, your children and their children after them may fear the Lord your God

  6. #6 peak

    two pieces, it is possible to fit the pieces together again to make a new shape. How many new shapes can you make?⏎Can you shunt the trucks so that the Cattle truck and the Sheep⏎truck change places and the Engine is

Steering

Push this neuron up or down while the model writes, and watch what changes. The outputs were generated ahead of time, so nothing runs in your browser.

turned down a lot
Prompt

Here is something I have been thinking about lately: I am going in the morning, and the house is still still off the house. It is a very quiet house of the moon, and the house of the planet. The planet of the earth is of the house of the planet. The

Most negative on

Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.

  1. #1 peak

    and showered us with love last year.⏎Today, we are posting the Economics– Important Questions Bank for Rajasthan Board HSC 2016 Examination to make life easy for all you HSC students.⏎Without making you wait any further,

  2. #2 peak

    price is one of the most critical procedures for bond investors, as miscalculating can lead to huge losses. But worry not. This calculator is built to make the process easier for you.⏎We have written this article to help you understand what

  3. #3 peak

    alveolus. The alveoli are tiny air sacs within the lungs where the exchange of oxygen and carbon dioxide takes place.⏎Last Editorial Review: 6/14/2012⏎Back to MedTerms online medical

  4. #4 peak

    before the party, we do not have known or seen the previous Congress, the Indian National Congress in the fight for India’s freedom. INC was established in the year 1885 the Theosophical Society of Indian and British members.

Connections

Show on map

Which neurons in earlier layers feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.

Fed by earlier layers

  1. L19:1228 excites
  2. L10:190 excites
  3. L18:477 excites
  4. L18:177 suppresses
  5. L13:1056 suppresses end of document boundary tokens
  6. L9:812 excites
  7. L9:429 excites
  8. L10:556 weakly excites
  9. L19:119 weakly suppresses
  10. L18:1018 weakly suppresses
  11. L15:59 weakly excites
  12. L10:1289 weakly suppresses
  13. L0:323 weakly suppresses
  14. L1:2401 weakly suppresses
  15. L9:146 weakly suppresses
  16. L19:2535 weakly excites
  17. L1:558 weakly suppresses
  18. L1:68 weakly excites
  19. L10:1032 weakly excites
  20. L6:1354 weakly excites
  21. L17:257 weakly excites
  22. L19:3040 weakly excites
  23. L0:480 weakly suppresses
  24. L3:59 weakly excites

Feeds later layers

  1. L21:1111 excites
  2. L21:2876 excites
  3. L23:914 excites
  4. L22:1186 excites
  5. L26:586 excites
  6. L27:616 weakly excites
  7. L24:306 weakly suppresses
  8. L22:631 weakly excites
  9. L23:1754 weakly suppresses
  10. L27:291 weakly excites
  11. L21:1541 weakly suppresses
  12. L24:36 weakly excites
  13. L21:1495 weakly excites
  14. L25:1722 weakly excites
  15. L22:2960 weakly suppresses
  16. L24:296 weakly suppresses
  17. L25:246 weakly suppresses
  18. L21:1352 weakly suppresses
  19. L22:1798 weakly suppresses
  20. L23:1860 weakly suppresses
  21. L23:2575 weakly suppresses
  22. L24:2157 weakly excites
  23. L24:627 weakly excites
  24. L24:840 weakly suppresses

Activation histogram

How often this neuron fires at each strength. Almost always it does close to nothing (the tall bars in the middle); the snippets above are the rare moments it fired hard, amber for positive and blue for negative.

1 values between -5.61 and -4.991 values between -4.99 and -4.371 values between -4.37 and -3.762 values between -3.76 and -3.145 values between -3.14 and -2.529 values between -2.52 and -1.909 values between -1.90 and -1.2924 values between -1.29 and -0.671352 values between -0.67 and -0.052398 values between -0.05 and 0.5779 values between 0.57 and 1.188 values between 1.18 and 1.803 values between 1.80 and 2.425 values between 2.42 and 3.042 values between 3.04 and 3.652 values between 4.27 and 4.892 values between 5.51 and 6.131 values between 9.21 and 9.831 values between 14.15 and 14.771 values between 16.62 and 17.241 values between 17.24 and 17.861 values between 18.48 and 19.09offnegativepositiveoften

Logit lens

The words this neuron nudges the model toward (amber) or away from (blue) when it fires. A hint, not a label: many neurons work through later layers instead.

Promotes

  1. rằng
  2. that
  3. _that
  4. →that
  5. että
  6. that
  7. asel
  8. ersed
  9. 、
  10. alion

Suppresses

  1. 瓒
  2. pNet
  3. atica
  4. очно
  5. OfClass
  6. -off
  7. очных
  8. Druid
  9. moon
  10. went