Neuron Explorer

Qwen3-0.6B

the word 'sales'

A neuron in layer 25 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 lights up on the word 'sales' in business and marketing text. When it was turned up, the model started repeating the word 'call' over and over.

Written by Claude from this neuron's activations and steering outputs. Confidence: high. 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

    . A white project manager with similar training and work experience was recently hired, and you find out that he will be paid more than you. You are a top salesperson for your

  2. #2 peak

    , including financial resources, market surveys, performance indicators and competitor performance statistics.⏎Business financial resources that may indicate strength during your SWOT analysis include financial resources derived from sales activities, income from investors and the value of company infrastructure. Strong financial performance will

  3. #3 peak

    on strengths. Performance indicators include rate of return on investment, production rates, sales growth, stock dividends, labor turnover rates and market share.⏎When you have completed

  4. #4 peak

    for the product.⏎You could make each category a separate view with each view in a block. Each view can have different criteria. You can give your CEO, sales manager, and marketing manager access to the block admin page and let them fight over

  5. #5 peak

    and oral);⏎- Marketing/selling skills (e.g., sales, publicity, fundraising);⏎- Scientific skills (e.g., lab skills, scientific

  6. #6 peak

    — is essential to any sales team. It enables teams to focus on exploring leads, fostering customer relationships, and

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: an economy that is physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical physical

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

    of criteria by which we all agree that it is “done”. This is a more rigorous definition than in other agile methodologies, where it is variously described as a “promise of

  2. #2 peak

    prototype?⏎- What are the benefits of low fidelity prototypes?⏎- What do wireframes look like?⏎- What is fidelity prototype?⏎- What is the main disadvantage of high fidelity prototyping?⏎- What is wireframe mockup

  3. #3 peak

    to coding best practices such as modular and reusable code, efficient algorithms, and proper documentation enhances the app’s maintainability and scalability. Embracing agile development methodologies and collaboration tools promotes effective teamwork and streamlines the development process.⏎Furthermore, continuous testing

  4. #4 peak

    UML represents a compilation of "best engineering⏎practices" which have proven successful in modelling large, complex systems.⏎UML succeeds the concepts of Booch, OMT and OOSE by fusing them into a single,⏎common and widely

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. L3:1558 suppresses
  2. L21:311 suppresses
  3. L18:779 suppresses
  4. L20:1140 weakly excites
  5. L0:2071 weakly excites
  6. L4:2629 weakly suppresses
  7. L6:2784 weakly suppresses
  8. L6:2007 weakly excites
  9. L9:2091 weakly excites
  10. L9:2356 weakly excites
  11. L22:2056 weakly suppresses
  12. L17:2308 weakly suppresses
  13. L21:1121 weakly excites
  14. L21:873 weakly suppresses
  15. L6:2944 weakly excites
  16. L9:2486 weakly suppresses
  17. L17:2956 weakly excites
  18. L5:1655 weakly suppresses
  19. L21:2944 weakly excites
  20. L8:1832 weakly suppresses
  21. L10:2740 weakly excites
  22. L16:2390 weakly suppresses
  23. L11:2301 weakly excites
  24. L10:1286 weakly suppresses

Feeds later layers

  1. L27:2652 weakly suppresses
  2. L26:2214 weakly excites
  3. L27:1437 weakly excites
  4. L26:2203 weakly excites
  5. L27:1012 weakly suppresses
  6. L26:1690 weakly suppresses
  7. L26:1917 weakly suppresses
  8. L27:418 weakly suppresses
  9. L27:1656 weakly excites
  10. L27:2835 weakly suppresses
  11. L26:2916 weakly suppresses
  12. L27:2048 weakly suppresses
  13. L27:2063 weakly excites
  14. L27:2185 weakly suppresses
  15. L26:1640 weakly suppresses
  16. L27:3008 weakly suppresses
  17. L27:29 weakly excites
  18. L27:2409 weakly excites
  19. L27:2189 weakly excites
  20. L26:1404 weakly suppresses
  21. L27:2698 weakly suppresses
  22. L27:2790 weakly suppresses
  23. L27:1375 weakly excites
  24. L26:1163 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.

3 values between -9.75 and -8.713 values between -7.66 and -6.614 values between -6.61 and -5.579 values between -5.57 and -4.5220 values between -4.52 and -3.4839 values between -3.48 and -2.4381 values between -2.43 and -1.39437 values between -1.39 and -0.342941 values between -0.34 and 0.70242 values between 0.70 and 1.7556 values between 1.75 and 2.7926 values between 2.79 and 3.8416 values between 3.84 and 4.887 values between 4.88 and 5.937 values between 5.93 and 6.984 values between 6.98 and 8.022 values between 8.02 and 9.072 values between 9.07 and 10.112 values between 10.11 and 11.163 values between 11.16 and 12.201 values between 14.29 and 15.341 values between 15.34 and 16.381 values between 17.43 and 18.471 values between 31.02 and 32.06offnegativepositiveoften

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. call
  2. führt
  3. OLL
  4. calls
  5. olla
  6. call
  7. klä
  8. 冈
  9. ナイ
  10. oll

Suppresses

  1. raphic
  2. economy
  3. ted
  4. Economy
  5. imm
  6. aking
  7. ewan
  8. econom
  9. economies
  10. Econom