Neuron Explorer

Qwen3-0.6B

'energy' in home energy topics

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 'energy' in articles about home heating, insulation and energy bills. When turned up, the model's writing drifted toward houses, heat and energy costs, but this was only loosely connected.

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

    energy bills.⏎WHERE DOES MY HOME LOSE ENERGY?⏎Superior energy efficiency mostly depends on creating a better air seal. Wall insulation is a significant issue in home energy savings, but there are other factors that will lower home energy efficiency.⏎Doors

  2. #2 peak

    winter heat loss and summer heat gain. Tight construction, good insulation and high-performance windows are key. "Weather stripping and caulking in existing homes can reduce your energy bill 10 to 25 percent," says David Johnston, president of

  3. #3 peak

    of the air leakage in a home.⏎As much as 40% of energy loss is due to air infiltration. Therefore, the most effective way to improve energy efficiency and comfort in your home is to seal it with foam.⏎LET’S COMP

  4. #4 peak

    the effects of climate change. Reference Energy System (RES) is a method of analysis for certain systems in particular scenarios. In this study, we examine a house energy system modelling under different circumstances. Our aim is to increase energy saving and use more

  5. #5 peak

    foam installations are carried out by Lapolla / AirTight licensed installers.⏎*See manufacturer guidelines and requirements.⏎HOME ENERGY ASSESSMENT⏎A home energy assessment helps owners determine where their house is losing energy and money – and how such

  6. #6 peak

    Post your comments<|endoftext|>Green buildings are designed, constructed and operated for the purpose of providing the occupants with a space that is both healthy and productive, while also being energy efficient and sustainable. Unfortunately, current approaches to green building design and construction don’t

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: In a small town, a group of friends are in a cozy, rural town hall. The only living, they are still in the same town. The next day, another day, and another. **Plot Summary: **

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

    explained that he suspected Samuel Robinson and the stranger as the real thieves. The authorities were not convinced. Pat Lyon was arrested and thrown in Walnut Street Prison.⏎Elsewhere in Philadelphia, Isaac Davis (the stranger Robinson had brought to the vault) began

  2. #2 peak

    he does it. There’s just one teensy, weensy problem.⏎Thomas never reached out and touched Jesus’ wounds. Not at all.⏎Meanwhile, in modern day Sunday school land, Thomas is the quick and easy way for teachers and

  3. #3 peak

    : Sam goes up as Hiroko zips down. And there, in the tree: one squirrel climbs up and another scurries down. Not far away, Daddy is quiet but Simon is LOUD, while a mother bird is silent as

  4. #4 peak

    to track the bear, but a snowstorm had obliterated the tracks. Search parties were sent out, but they found no trace of the dead cook. Meanwhile, Ryan made himself scarce while the men were out searching, and no one ever found

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. L7:174 suppresses
  2. L6:2442 weakly suppresses
  3. L6:1832 weakly suppresses
  4. L6:1272 weakly excites
  5. L7:802 weakly excites
  6. L5:347 weakly suppresses
  7. L4:1589 weakly excites
  8. L5:1744 weakly suppresses
  9. L0:1603 weakly suppresses
  10. L6:2259 weakly excites
  11. L2:235 weakly suppresses
  12. L0:696 weakly excites
  13. L0:1832 weakly suppresses
  14. L4:2779 weakly suppresses
  15. L4:1579 weakly suppresses
  16. L5:3043 weakly suppresses
  17. L6:1537 weakly excites
  18. L3:2546 weakly excites
  19. L0:1293 weakly excites
  20. L0:2831 weakly excites
  21. L1:2922 weakly excites
  22. L3:1361 weakly excites
  23. L1:1889 weakly excites
  24. L6:881 weakly excites

Feeds later layers

  1. L11:917 excites
  2. L15:1552 weakly excites
  3. L17:2810 weakly excites
  4. L12:2872 weakly excites
  5. L20:2466 weakly excites
  6. L18:1816 weakly excites
  7. L14:2094 weakly suppresses
  8. L13:2979 weakly suppresses
  9. L10:1009 weakly excites
  10. L17:2737 weakly excites
  11. L15:2781 weakly excites
  12. L16:2899 weakly suppresses
  13. L9:1633 weakly excites
  14. L11:2213 weakly suppresses
  15. L14:2132 weakly excites
  16. L11:2950 weakly excites
  17. L20:1150 weakly excites
  18. L12:1738 weakly excites
  19. L20:2562 weakly excites
  20. L10:670 weakly excites
  21. L9:2290 weakly suppresses
  22. L25:2329 weakly excites
  23. L14:2655 weakly suppresses
  24. L12:1044 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 -2.00 and -1.803 values between -1.39 and -1.193 values between -1.19 and -0.995 values between -0.99 and -0.7814 values between -0.78 and -0.5839 values between -0.58 and -0.38408 values between -0.38 and -0.171984 values between -0.17 and 0.031204 values between 0.03 and 0.23194 values between 0.23 and 0.4430 values between 0.44 and 0.644 values between 0.64 and 0.846 values between 0.84 and 1.054 values between 1.05 and 1.252 values between 1.25 and 1.451 values between 1.45 and 1.661 values between 2.27 and 2.471 values between 2.67 and 2.881 values between 3.89 and 4.101 values between 5.93 and 6.13offnegativepositiveoften

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. ieten
  2. ensible
  3. 箅
  4. ��
  5. ','',
  6. ration
  7. /rfc
  8. enci
  9. [state
  10. ','');⏎

Suppresses

  1. serial
  2. orneys
  3. лав
  4. kode
  5. untos
  6. ultrasound
  7. standing
  8. INAL
  9. laughter
  10. hold