Neuron Explorer

Qwen3-0.6B

'of' after a noun

A neuron in layer 8 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 'of' when it follows a noun, as in 'the results of', 'the formula of' or 'copyright of'. When it was turned up strongly, the output broke into Chinese text and filler characters, so the steering result does not match the trigger.

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

    If you haven't already taken a look at the articles, I hope you will find some time to check them out. I encourage you to read the first article of the following list.⏎If you want to liven up your chemistry course with some

  2. #2 peak

    signed up to receive the notifications of new studies, you can do that today (the form is at the bottom of

  3. #3 peak

    productivity of cast aluminum, are widely used in the production of semi-continuous casting and die castings.⏎Foam Ceramic Filter Manufacturing Process⏎The main raw material of the porous filter material is high-temperature alumina. It does not react with

  4. #4 peak

    . But, where registration is available, many authors register anyway, especially for works that are sold for money. That is because registration helps to prove that the copyright of a work belongs to a certain author.⏎If an author gets paid to make a

  5. #5 peak

    standard contribution is used when the marginal cost is using.⏎Sales Volume Variance Formula⏎In general, the formula of Sales Volume Variance is⏎Sales Volume Variance = (Actual units sold –

  6. #6 peak

    questions give students a sneak preview of what to expect on the test. Furthermore, students can look at the results of a practice test to determine which skills they need to work on.⏎Some students may

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: the fact that, in the context of a non-profit, the development of a certain amount of information and which is directly related to the content of the information, the information will first and foremost be determined by the level and the overall situation of

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

    unique way and this has created dualities of value that is often difficult for others to understand (Chattergee 1991, Garg/Parikh 1995). Other than any other countries Indian managers gave lot more

  2. #2 peak

    will protect your home against air pollutants<|endoftext|>Active and Passive Voice – Tips for Content Writing⏎February 22nd, 2012 by Donna Mathews⏎The use of active voice is important while writing online content. It improves the

  3. #3 peak

    and teachers?⏎According to the Montana Common Core Standards<|endoftext|>Copyright © 1995 Brother Eric Vogel, St. Mary's College⏎Balsamorhiza hookeri Nut

  4. #4 peak

    Effective technical communication is honest, clear, accurate, comprehensive, accessible, concise, professional in appearance, and correct.” – Mike Markel⏎Technical writing is used in many technical and professional fields. Its goal is to

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. L1:25 suppresses
  2. L5:176 suppresses
  3. L7:92 weakly suppresses
  4. L3:53 weakly excites
  5. L5:136 weakly excites
  6. L5:2120 weakly excites
  7. L3:249 weakly excites
  8. L0:769 weakly suppresses
  9. L6:13 weakly excites
  10. L3:171 weakly suppresses
  11. L2:1570 weakly suppresses
  12. L3:805 weakly suppresses
  13. L4:342 weakly excites
  14. L7:1734 weakly suppresses
  15. L7:3013 weakly suppresses
  16. L4:471 weakly excites
  17. L3:2817 weakly suppresses
  18. L7:3034 weakly suppresses
  19. L2:2912 weakly excites
  20. L3:1870 weakly excites
  21. L4:552 weakly suppresses
  22. L3:2731 weakly suppresses
  23. L3:1172 weakly suppresses
  24. L1:1227 weakly suppresses

Feeds later layers

  1. L9:281 strongly excites
  2. L9:207 strongly excites
  3. L10:370 suppresses
  4. L9:46 suppresses
  5. L9:147 excites
  6. L18:477 suppresses
  7. L11:840 suppresses
  8. L10:1032 excites
  9. L9:537 excites
  10. L21:525 excites
  11. L9:232 excites
  12. L18:233 suppresses
  13. L17:758 excites
  14. L16:1519 excites
  15. L20:395 excites
  16. L17:2202 excites
  17. L10:602 excites
  18. L19:2338 excites
  19. L18:646 excites
  20. L18:950 weakly excites
  21. L10:197 weakly excites
  22. L9:530 weakly excites
  23. L26:687 weakly excites
  24. L15:3035 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 -0.86 and -0.781 values between -0.78 and -0.714 values between -0.71 and -0.633 values between -0.63 and -0.568 values between -0.48 and -0.4115 values between -0.41 and -0.3352 values between -0.33 and -0.26100 values between -0.26 and -0.18253 values between -0.18 and -0.11640 values between -0.11 and -0.031724 values between -0.03 and 0.05656 values between 0.05 and 0.12274 values between 0.12 and 0.2092 values between 0.20 and 0.2736 values between 0.27 and 0.3517 values between 0.35 and 0.4211 values between 0.42 and 0.506 values between 0.50 and 0.573 values between 0.57 and 0.653 values between 0.65 and 0.732 values between 0.73 and 0.802 values between 0.80 and 0.881 values between 0.88 and 0.951 values between 0.95 and 1.031 values between 1.18 and 1.251 values between 1.25 and 1.331 values between 2.08 and 2.16offnegativepositiveoften

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. Xiao
  2. jiang
  3. imizer
  4. итесь
  5. wang
  6. ้อน
  7. hua
  8. mak
  9. .ibatis
  10. тся

Suppresses

  1. CppType
  2. 也为
  3. 回合
  4. 腓
  5. �回
  6. Beth
  7. ölçü
  8. 数额
  9. uspendLayout
  10. Brussels