Neuron Explorer

Qwen3-0.6B

'the' before 'idea', 'view' or 'impression'

A neuron in layer 20 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 'the' when the next word is likely to be an abstract noun such as 'idea', 'view', 'purpose' or 'impression', as in 'lends credence to the idea'. When it was turned up, the model fell into loops of the word 'idea', which is the word it pushes toward.

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

    targets for attacks because “they don’t have anything worth stealing.”⏎Short for malicious software, malware refers to any program that is introduced into the target's computer with the purpose of causing damage, gaining unauthorized access, or displaying unwanted advertising. Under the

  2. #2 peak

    since it rode to earth in a meteorite, validating the Panspermia theory of how life came to this planet?⏎Or does it lend credence to the idea that life could spring from inanimate material on this planet by showing that it

  3. #3 peak

    of different ways, including the ‘Belief in a Just World’ theory. The ‘Belief in a Just World’ theory states that people tend to harbour the view that bad things cannot happen to good people because the world we live in is

  4. #4 peak

    amendment to the Equal Pay Act of 1963, (S. 182) was introduced by Congress in 2011 with the support of President Obama, who in a statement called the legislation “ a common-s

  5. #5 peak

    . That said, here are three challenges virtual learners may face and suggestions on how to overcome them.⏎🤔 Challenge: Students Passiveness⏎Anyone who teaches has faced the challenge

  6. #6 peak

    two important principles are employed when prescribing medicines: the minimum dose and the single dose.⏎The principle that only ‘the minimum dose’ should be employed is based upon the understanding that the stimulus of the medicine triggers the intrinsic healing response. Following this principle

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: what if we, as a society, if we do not go to a certain something or something else, we should something or something else. *This is a how to a someone, if we should do something, where we should go to

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

    0 PM we will be having fun with our "Structures & Materials" activity, where children and parents will get to read the book “The True Story of the Three Little Pigs” by Jon Scieszka, build and test of the

  2. #2 peak

    War on Terror’. Curiously, despite their proliferation, they have received relatively little academic attention. In A Theory of the Drone, French philosopher Grégoire Chamayou seeks to comprehend how drones

  3. #3 peak

    worrying number of omissions, errors, inconsistencies, and that it also employs flawed methodologies. It lays out concerns that it legitimises and strengthens a false narrative of the role that fin-tech can play in poverty alleviation and development, with potentially devastating

  4. #4 peak

    Standards which was published in 1996. It has been extensively revised and updated to take account of the latest finding of the United Nations Scientific Committee on the Effects of Atomic Radiation, and the latest recommendations of the International Commission on Radiological

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. L19:1767 suppresses
  2. L19:376 excites
  3. L19:1714 suppresses
  4. L18:2452 suppresses
  5. L16:419 excites
  6. L18:958 suppresses
  7. L8:197 suppresses
  8. L4:52 excites
  9. L19:1796 suppresses
  10. L17:2215 suppresses
  11. L16:792 excites "the" inside a prepositional phrase
  12. L17:30 suppresses
  13. L12:1168 weakly excites
  14. L19:2413 weakly excites
  15. L16:2204 weakly excites
  16. L13:2405 weakly excites
  17. L18:1087 weakly suppresses
  18. L14:1818 weakly excites
  19. L19:2611 weakly suppresses
  20. L17:1719 weakly suppresses
  21. L12:435 weakly suppresses
  22. L16:2727 weakly suppresses
  23. L18:2137 weakly suppresses "just" as an emphasis word
  24. L15:887 weakly excites

Feeds later layers

  1. L21:2342 strongly excites
  2. L27:127 suppresses
  3. L27:814 excites
  4. L27:399 excites
  5. L22:3060 excites
  6. L26:507 excites
  7. L21:831 excites
  8. L21:1951 excites
  9. L26:532 excites
  10. L25:423 suppresses
  11. L27:592 weakly excites
  12. L22:438 weakly excites
  13. L23:2369 weakly excites
  14. L27:588 weakly excites
  15. L21:1409 weakly excites
  16. L24:1366 weakly suppresses
  17. L21:596 weakly excites
  18. L21:2925 weakly excites
  19. L22:2736 weakly excites
  20. L25:2342 weakly excites
  21. L21:2461 weakly excites
  22. L23:94 weakly suppresses
  23. L22:1645 weakly excites
  24. L23:79 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 -4.48 and -4.045 values between -4.04 and -3.592 values between -3.59 and -3.158 values between -3.15 and -2.718 values between -2.71 and -2.278 values between -2.27 and -1.8221 values between -1.82 and -1.3831 values between -1.38 and -0.94134 values between -0.94 and -0.491138 values between -0.49 and -0.052111 values between -0.05 and 0.39379 values between 0.39 and 0.8436 values between 0.84 and 1.287 values between 1.28 and 1.724 values between 1.72 and 2.173 values between 2.17 and 2.612 values between 2.61 and 3.053 values between 3.50 and 3.941 values between 4.38 and 4.822 values between 5.27 and 5.711 values between 6.60 and 7.041 values between 12.80 and 13.24offnegativepositiveoften

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. idea
  2. notion
  3. concept
  4. idea
  5. 概念
  6. concept
  7. assumption
  8. Idea
  9. fact
  10. phenomenon

Suppresses

  1. ersed
  2. IFI
  3. ToFront
  4. ductory
  5. How
  6. Everything
  7. ed
  8. Middleton
  9. undai
  10. Ahead