Neuron Explorer

Qwen3-0.6B

'instead of' and 'rather than'

A neuron in layer 17 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 lights up on the word that follows 'instead' or 'rather', such as 'of', 'than' or 'try', when a sentence sets one way of doing something against another. Turning it up did not make the output show this idea, though, so the steered text does not clearly reflect it.

Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens an email to the maker with the neuron already filled in).

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

    <|endoftext|>The move to electronic health records is in full swing for most of the medical community, but holdouts point to security issues as an argument to keep their records on paper.⏎The news is riddled with stories about data being compromised these days,

  2. #2 peak

    the stage where you use technology to substitute what you could have done with pen and paper. one popular example of this is using word processor to type a story instead of handwriting it.⏎This is where technology is used to carry out learning tasks in relatively

  3. #3 peak

    is a distributor as well. Jeffrey Humphries is the contact that I know of for us Canadians, eh.⏎Breakout EDU has gone Digital too! Rather than having kids work on their own

  4. #4 peak

    example, your tomato ketchup or mayonnaise⏎- Stop using plastic drinking straws and instead try metal, paper, or even wheat straws⏎- Swap tampons and pads

  5. #5 peak

    your face. Do not forget to clean your headphones regularly.⏎- Use voice commands⏎- Nowadays, AI is becoming more intelligent. We can use voice commands instead of typing on the screen.⏎- Avoid sharing your devices with others⏎- If unnecessary

  6. #6 peak

    is transported in containers. Worldwide, more than 400 ports have the capability to handle containers.⏎Many ocean carriers are now shipping cargoes in containers rather than break bulk. Generally<|endoftext|>CDPATH is an environment variable

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 is the purpose of this is only a single purpose, and what is the purpose of this is only a single purpose is only a single purpose, and the purpose of this is only a single purpose is only a single purpose is only a

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

    be ruled out. A step-by-step approach should be used to identify a possible DISR:⏎1. Complete a drug history. Reconciliation of all prescription and nonprescription agents, as well as any natural medicines, should be completed. Develop

  2. #2 peak

    to have actinic keratoses. The incidence is slightly higher in men, because they tend to spend more time in the sun and use less sun protection than women do. African-Americans, Hispanics, Asians and others with darker

  3. #3 peak

    Engineering. “This is one area of stem cell biology where human and mouse differ significantly and we never would have discovered this if we had limited our studies to using only mouse embryonic stem cells. Adult human stem cells just didn’t work for this

  4. #4 peak

    here.⏎If you would like to support the mission of Open Culture, consider making a donation to our site. It’s hard to rely 100% on ads, and your contributions will help us continue providing the best free cultural and educational

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. L15:2838 suppresses
  2. L16:2561 suppresses
  3. L16:697 suppresses
  4. L12:1954 suppresses 'with' or 'from' after comparison words
  5. L16:2278 suppresses
  6. L12:1834 suppresses
  7. L11:1215 suppresses
  8. L12:2471 suppresses
  9. L16:793 excites
  10. L13:634 excites
  11. L14:1413 excites
  12. L14:172 excites
  13. L14:1178 suppresses
  14. L16:2252 suppresses
  15. L13:2269 suppresses
  16. L10:2736 weakly excites
  17. L15:2057 weakly excites
  18. L1:1082 weakly suppresses
  19. L9:952 weakly excites
  20. L6:1386 weakly excites
  21. L16:1616 weakly excites
  22. L16:2986 weakly suppresses
  23. L5:2269 weakly excites
  24. L10:2924 weakly suppresses

Feeds later layers

  1. L18:2433 excites
  2. L19:1893 excites
  3. L22:1497 excites
  4. L26:2116 excites
  5. L21:886 weakly suppresses
  6. L23:871 weakly excites
  7. L21:3000 weakly excites
  8. L25:943 weakly excites
  9. L24:2188 weakly excites
  10. L19:2897 weakly suppresses
  11. L19:1408 weakly excites
  12. L18:1423 weakly excites
  13. L20:618 weakly suppresses
  14. L22:1207 weakly excites
  15. L19:2484 weakly suppresses
  16. L21:1932 weakly excites
  17. L22:1720 weakly excites
  18. L23:2358 weakly excites
  19. L18:1892 weakly suppresses
  20. L25:2846 weakly suppresses
  21. L18:255 weakly suppresses
  22. L20:1132 weakly suppresses
  23. L20:1525 weakly excites
  24. L20:1920 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.

1 values between -3.18 and -2.981 values between -2.78 and -2.592 values between -2.39 and -2.194 values between -2.19 and -1.992 values between -1.99 and -1.807 values between -1.80 and -1.607 values between -1.60 and -1.409 values between -1.40 and -1.2018 values between -1.20 and -1.0125 values between -1.01 and -0.8149 values between -0.81 and -0.6188 values between -0.61 and -0.41277 values between -0.41 and -0.221176 values between -0.22 and -0.021735 values between -0.02 and 0.18335 values between 0.18 and 0.3887 values between 0.38 and 0.5829 values between 0.58 and 0.7717 values between 0.77 and 0.9710 values between 0.97 and 1.177 values between 1.17 and 1.373 values between 1.37 and 1.564 values between 1.56 and 1.763 values between 1.76 and 1.963 values between 1.96 and 2.162 values between 2.16 and 2.351 values between 2.35 and 2.553 values between 3.14 and 3.341 values between 4.13 and 4.332 values between 4.53 and 4.72offnegativepositiveoften

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. 手工
  2. 手动
  3. manually
  4. raw
  5. (raw
  6. 直接
  7. directly
  8. manual
  9. 亲手
  10. direct

Suppresses

  1. 水量
  2. rends
  3. 溶解
  4. しよう
  5. intentions
  6. 誉
  7. ?\
  8. imbus
  9. 治理体系
  10. ーズ