Neuron Explorer

Qwen3-0.6B

'et' in 'et al.' citations

A neuron in layer 12 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 'et' in academic citations like 'Smith et al.', where the next word is predicted to be 'al.'. Turning it up did not make the writing about citations.

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

    influence of aerosols on the global climate.⏎Ault, A.P., et al. “Raman Microspectroscopy and Vibrational Sum Frequency Generation Spect

  2. #2 peak

    promising approach to prevent deteriorated adiposity values among this high-risk population,” the researchers wrote.⏎Bélanger M, Dugar C, Perron J, et al. Association between lifestyle habits and adiposity values among children exposed and unex

  3. #3 peak

    marked ecological changes, including alterations to climatic regimes, phenology, resource availability and habitat quality (Zhou et al. 2004; Grimm et al. 2008). Consequently, growth in urban development is a

  4. #4 peak

    ious complications are uncommon.⏎Broaddus VC, Light RW. Pleural effusion. In: Mason RJ, Murray JF, Broaddus VC, et al., eds. Murray and Nadel's Textbook of Respiratory Medicine.

  5. #5 peak

    fever. The effect on mastoidectomy is unclear, but a clinically important increase seems unlikely. (Level of Evidence: 2c)⏎Sharland M, et al. Antibiotic prescribing in general practice and hospital admissions for peritonsill

  6. #6 peak

    ators through competition, and maintenance of a functional balance of biodiversity in the local community (Krebs et al., 1995; Terborgh et al., 1999; Logan & Sweanor, 2

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 information I have been given, the information I have been given, and the information that is in the food I have been told, in the food I have been told, or the food I have been told, or the food I have

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

    risk for wandering astronauts, he adds, but there would be time to return to a shielded base.⏎To continue reading this article, subscribe to receive access to all of newscientist.com, including 20 years of archive content.<|endoftext|>

  2. #2 peak

    replace human translation. Neither BioOne nor the owners and publishers of the content make, and they explicitly disclaim, any express or implied representations or warranties of any kind, including, without limitation, representations and warranties as to the functionality of the translation

  3. #3 peak

    Look-up table method⏎Create Volcano (or Atoll) martix. It is an extension of Bullseye matrix problem.⏎Who has power to do everything in this world?⏎Close MATLAB with keyboard⏎Find the treasures in MATLAB Central and

  4. #4 peak

    will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.<|endoftext|>- Major Systems >⏎- The Plumbing Rough-In⏎The Plumbing Rough-In

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. L4:543 suppresses
  2. L10:2724 excites
  3. L9:1539 excites
  4. L6:2654 suppresses
  5. L7:727 excites
  6. L3:990 excites
  7. L11:240 weakly excites
  8. L10:157 weakly suppresses end of document and web boilerplate
  9. L1:2695 weakly excites
  10. L7:755 weakly suppresses
  11. L6:1175 weakly suppresses
  12. L9:751 weakly suppresses
  13. L5:1552 weakly suppresses
  14. L11:607 weakly excites
  15. L11:1785 weakly suppresses
  16. L8:1455 weakly suppresses
  17. L10:183 weakly suppresses
  18. L6:390 weakly suppresses
  19. L6:2811 weakly excites
  20. L6:1868 weakly excites
  21. L11:2667 weakly excites
  22. L4:1529 weakly excites
  23. L2:2673 weakly excites
  24. L0:2594 weakly excites

Feeds later layers

  1. L15:1740 excites
  2. L15:2148 weakly excites
  3. L14:1263 weakly excites
  4. L13:1419 weakly excites
  5. L13:1118 weakly excites
  6. L16:1127 weakly suppresses opening bracket after an imperial measurement
  7. L18:1811 weakly excites 'and' linking two descriptive claims
  8. L16:3039 weakly excites
  9. L21:2438 weakly suppresses
  10. L26:1448 weakly suppresses
  11. L14:1738 weakly excites
  12. L21:593 weakly excites
  13. L15:1930 weakly excites
  14. L14:628 weakly excites end of document boundary token
  15. L21:441 weakly excites
  16. L15:541 weakly excites
  17. L23:792 weakly suppresses
  18. L14:3001 weakly excites
  19. L20:1938 weakly suppresses
  20. L14:362 weakly excites
  21. L19:1713 weakly excites
  22. L15:178 weakly excites
  23. L18:2722 weakly excites
  24. L16:486 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.

3 values between -1.09 and -0.7164 values between -0.71 and -0.332492 values between -0.33 and 0.041331 values between 0.04 and 0.4213 values between 0.42 and 0.801 values between 1.18 and 1.561 values between 1.93 and 2.311 values between 4.20 and 4.581 values between 5.33 and 5.711 values between 13.65 and 14.02offnegativepositiveoften

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. Emin
  2. GMEM
  3. .CreateCommand
  4. 之意
  5. thereof
  6. Kensington
  7. Words
  8. 五大
  9. 亿美元
  10. ants

Suppresses

  1. rier
  2. bral
  3. heiro
  4. 笼
  5. >"+⏎
  6. _ENTER
  7. plementary
  8. 嗓子
  9. tero
  10. ><![