Neuron Explorer

Qwen3-0.6B

responsible investing and ESG terms

A neuron in layer 6 of Qwen3-0.6B. Its strongest snippets are mixed: they peak on different tokens. It is featured, so it has steering outputs.

What this neuron does

This neuron responds to business and money words about doing good, such as the 'Responsible' in Socially Responsible Investing or 'chain' in supply chain. When turned up, the model tended to drift toward talk about companies, climate and sustainability.

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

    didn’t realize it at the time, but he was already practicing socially responsible investing.⏎What is Socially Responsible Investing?⏎Socially responsible investing (sometimes also called Ethical Investing) is exactly

  2. #2 peak

    will also skip companies who don’t engage in socially responsible behavior (like coffee/restaurant companies who don’t use fair trade beans, for example). Socially responsible investing (SRI) is basically the practice of putting your money to work only in

  3. #3 peak

    + community. As we’ll discuss in a minute, you are free to make your own choices about what is (and isn’t) socially responsible.⏎Ethical Investing is More Popular Than Ever⏎These days, there are a growing number of people

  4. #4 peak

    that can record transactions and information in a secure and transparent manner.⏎Blockchain has the potential to disrupt industries that rely on trust and verification, such as finance, supply chain management, and voting systems. It eliminates the need for intermediaries and enables secure

  5. #5 peak

    curbs on emissions, for example an international carbon price. A carbon price of $50 per tonne emitted is already accounted for by some companies, CDP said.⏎If it were to be introduced

  6. #6 peak

    peace Canada delegation arrived in Oslo Monday. Two of the delegates, Andrew Nikiforuk and Dr. John O'Connor, have raised concerns about the environmental, social and financial risks of tar sands investments that are reverberating through the Nordic business

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: 20.5, 20.5, 20.5, 20.5, 20.5, 20.5, 20.5, 20.5,

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

    U.N) shows that, while prices are once again down from a peak, a troublesome volatility started to affect food prices this decade. These are the very

  2. #2 peak

    form and as a result it begins to crystallize. It doesn’t affect the performance of the candle in any way and also means your wax<|endoftext|>Equalization - Sound Mixing.⏎May

  3. #3 peak

    are betting that the price of the security will rise, allowing you to get a good deal later. By selling futures contracts, you are indicating that you are bearish about Bitcoin and that you predict a price decline.⏎- Prediction Markets⏎Shorting

  4. #4 peak

    pickup in “headline” inflation. However, core inflation has also increased; the year-over-year core CPI (excluding volatile food and energy prices) moved from a record low of 0.6 percent in October 2010 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. L3:1346 suppresses
  2. L4:2409 excites
  3. L4:2651 suppresses
  4. L4:2954 suppresses
  5. L5:91 weakly excites
  6. L3:2584 weakly suppresses
  7. L3:928 weakly excites
  8. L5:258 weakly excites
  9. L3:464 weakly excites
  10. L2:2261 weakly suppresses
  11. L4:1671 weakly excites
  12. L3:258 weakly suppresses
  13. L5:50 weakly excites
  14. L5:353 weakly suppresses
  15. L1:2804 weakly excites
  16. L3:1702 weakly suppresses
  17. L4:2414 weakly excites
  18. L5:748 weakly excites
  19. L2:1494 weakly suppresses
  20. L5:96 weakly suppresses
  21. L3:66 weakly excites
  22. L3:1337 weakly suppresses
  23. L5:2135 weakly excites
  24. L0:4 weakly suppresses

Feeds later layers

  1. L7:2399 suppresses
  2. L7:1999 excites
  3. L8:2769 suppresses
  4. L7:1857 excites
  5. L10:1683 excites
  6. L7:1291 excites
  7. L7:1259 excites
  8. L7:2603 suppresses
  9. L7:2108 suppresses
  10. L15:2970 excites
  11. L19:2752 excites
  12. L10:2048 weakly suppresses
  13. L7:1303 weakly suppresses
  14. L7:1030 weakly suppresses
  15. L9:2662 weakly excites
  16. L11:1869 weakly excites
  17. L18:2298 weakly suppresses
  18. L9:1548 weakly suppresses
  19. L9:1018 weakly suppresses
  20. L22:1444 weakly suppresses
  21. L8:2711 weakly suppresses
  22. L20:1864 weakly suppresses
  23. L9:772 weakly suppresses
  24. L7:2930 weakly excites

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.

2 values between -1.22 and -1.151 values between -0.85 and -0.782 values between -0.70 and -0.6310 values between -0.63 and -0.5525 values between -0.55 and -0.4840 values between -0.48 and -0.4090 values between -0.40 and -0.33189 values between -0.33 and -0.25325 values between -0.25 and -0.18542 values between -0.18 and -0.10771 values between -0.10 and -0.03862 values between -0.03 and 0.05505 values between 0.05 and 0.12291 values between 0.12 and 0.20143 values between 0.20 and 0.2749 values between 0.27 and 0.3525 values between 0.35 and 0.4221 values between 0.42 and 0.504 values between 0.50 and 0.572 values between 0.57 and 0.652 values between 0.65 and 0.721 values between 0.72 and 0.801 values between 0.87 and 0.942 values between 0.94 and 1.021 values between 1.17 and 1.241 values between 1.39 and 1.471 values between 1.69 and 1.77offnegativepositiveoften

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. uts
  2. _IRQn
  3. uri
  4. source
  5. .jsx
  6. yard
  7. stry
  8. <source
  9. .names
  10. upro

Suppresses

  1. ставлен
  2. pressions
  3. SETTING
  4. Kou
  5. DropDown
  6. ировки
  7. тем
  8. RESET
  9. ifferential
  10. olley