Neuron Explorer

Qwen3-0.6B

'had' after has or have

A neuron in layer 2 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 responds to the word "had" when it comes straight after "has", "have" or "haven't", as in "has had a significant impact". Turning it up did not produce writing that clearly shows this pattern.

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

    Bronfenbrennerdeveloped the ecological model ofhuman development. Urie Bronfenbrenner8217;s ecological model of human development has had essay junk food should be banned enduring impact ambition essay on macbeth thefield of

  2. #2 peak

    or they haven’t had the proper training. It’s up to the manager from this point to ensure the

  3. #3 peak

    generation that has had such a chance for peace, for development, for wealth, for freedom for other

  4. #4 peak

    -dimensional plastic objects and polymer films. The recent introduction of high-density atmospheric plasma for film, foil, paper, foam, nonwoven and woven substrate applications has had a significant impact on the surfaces of these materials at considerably lower capitalization costs.⏎

  5. #5 peak

    Natural Capital Accounting, or NCA. Through NCA, natural resources can be mainstreamed into development policy and planning. This video captures the impact that accounting has had on policy-making in Indonesia.⏎Last year, WAVES program stated that “A

  6. #6 peak

    grains come in many shapes and sizes, from large kernels of popcorn to small quinoa seeds.⏎- Whole grains. These are unrefined grains that haven't had their bran and germ removed

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: been given to a given the following 100% for the given given given given given given given given given given given given given given given given given given given given given given given given given given given given given given given given given given

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

    would also affect us as without any doubt.⏎Enormous amount of plastic waste are overflowing

  2. #2 peak

    historian working within the Classic Catholic Framework (CCF) will face all the diverse and varied expressions of Christian belief brought forth from the relevant texts. He will, however, ask different questions about those texts from those who work in the CPF or the

  3. #3 peak

    of clothing should also keep the heat away from the body of the person wearing it.⏎Facility Clothing

  4. #4 peak

    should also meet healthcare standards for washability, mold and microbial resistance, and fire safety.

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. L0:1730 weakly excites
  2. L1:1055 weakly excites
  3. L1:2411 weakly suppresses
  4. L0:1228 weakly suppresses
  5. L1:1693 weakly suppresses
  6. L0:580 weakly suppresses
  7. L1:139 weakly excites
  8. L0:377 weakly excites
  9. L1:135 weakly suppresses
  10. L1:1662 weakly suppresses
  11. L1:3000 weakly suppresses
  12. L0:1541 weakly suppresses
  13. L1:1321 weakly suppresses
  14. L1:604 weakly excites
  15. L0:2474 weakly suppresses
  16. L0:732 weakly excites
  17. L1:838 weakly suppresses 'be' after modal verbs like 'can'
  18. L1:2872 weakly suppresses
  19. L1:1561 weakly excites
  20. L0:1301 weakly suppresses
  21. L0:2587 weakly excites
  22. L1:491 weakly excites
  23. L1:2128 weakly excites
  24. L0:2095 weakly suppresses

Feeds later layers

  1. L3:309 excites
  2. L4:113 suppresses
  3. L3:2198 suppresses
  4. L7:1406 excites
  5. L8:403 suppresses
  6. L4:124 suppresses
  7. L18:2266 weakly suppresses
  8. L14:622 weakly suppresses
  9. L3:1202 weakly excites
  10. L3:756 weakly excites
  11. L14:2417 weakly suppresses
  12. L4:1043 weakly excites
  13. L9:95 weakly suppresses
  14. L21:61 weakly suppresses
  15. L16:1935 weakly excites
  16. L9:1903 weakly excites
  17. L20:1338 weakly excites
  18. L6:2398 weakly excites
  19. L4:48 weakly suppresses
  20. L12:124 weakly suppresses
  21. L10:3016 weakly suppresses
  22. L7:1580 weakly excites
  23. L14:898 weakly excites
  24. L4:2128 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.

1 values between -4.15 and -3.991 values between -2.39 and -2.231 values between -2.23 and -2.071 values between -1.75 and -1.591 values between -1.59 and -1.432 values between -1.11 and -0.954 values between -0.95 and -0.796 values between -0.79 and -0.6339 values between -0.63 and -0.4762 values between -0.47 and -0.31185 values between -0.31 and -0.151878 values between -0.15 and 0.011556 values between 0.01 and 0.17144 values between 0.17 and 0.3315 values between 0.33 and 0.496 values between 0.49 and 0.652 values between 0.65 and 0.812 values between 0.81 and 0.971 values between 0.97 and 1.131 values between 2.09 and 2.25offnegativepositiveoften

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. электро
  2. groupName
  3. orer
  4. 硬度
  5. ぶり
  6. mse
  7. ,filename
  8. masa
  9. filename
  10. ạp

Suppresses

  1. vent
  2. thers
  3. S
  4. donn
  5. ic
  6. Literal
  7. ley
  8. ��
  9. ************************************************************************
  10. ox