Neuron Explorer

Qwen3-0.6B

'as' in 'as well as' and 'as much as'

A neuron in layer 17 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 "as" in set phrases like "as well as", "as much as possible" and "as a result". Turning it up did not produce any clear change in the text the model wrote.

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

    Oracle With Clause Syntax and Examples :⏎In this section i would like to explain the syntax as well as examples of With clause in oracle.Before checking the syntax and examples of With

  2. #2 peak

    protect the earth’s climate. The global climate crisis is non-negotiable. #Move the Date: We need to do everything we can to delay the date as much as possible.⏎At VAUDE, we have already set out to reduce

  3. #3 peak

    With Clause is useful in Recursive queries as well.⏎These are some important points of With Clause in oracle. In following section i would like to explain about the syntax as well as multiple examples of with clause.⏎With SQL_Query_Name As⏎Select *

  4. #4 peak

    (University of Manchester), whose expertise lays in sustainable foods and food groups.⏎The event attracted an audience of 70, including the members of the general public as well as staff and students from the University of Nottingham and featured a lively debate on

  5. #5 peak

    work on the same piece? This section needs some elaboration. --EvanProdromou⏎Collaborative graphic design using software as a mediation device has some disadvantages, compared to collaborative development of text.⏎- Little

  6. #6 peak

    topic, which will take some time. World War 2 is such a broad theme that in order to write a profound essay, you need to narrow your topic as much as possible. Otherwise, you will write about everything and nothing at the same

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: 2-12-2-12-12-3-3-2-13-3-3-3-24-3-28-2-3-2-4-3-2

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

    ecosystem approach principles into policy instruments, planning processes, and sectoral plans (e.g., in forest, fisheries, agriculture). At a more local level the principles of the ecosystem approach can be used to guide the development

  2. #2 peak

    schemes are rarely outweighed by the socioeconomic benefits accrued to translocated farmers," they write. "At an average start-up resettlement cost of at least US$12,00

  3. #3 peak

    and carried high-quality weapons and armour.⏎A key part of a Carolingian soldier’s armour was the shield which was critically essential for use on the battlefield at a time when lances

  4. #4 peak

    harm, similar to viruses. The average computer user arguably has no need to understand the intricacies of spyware, or any other form of malware. But at a minimum, they should be cognizant that it is malicious software that collects personal

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. L6:328 strongly suppresses
  2. L2:8 strongly suppresses
  3. L10:103 strongly excites
  4. L0:481 strongly suppresses
  5. L2:1699 strongly excites
  6. L1:542 strongly suppresses
  7. L7:520 strongly suppresses
  8. L16:84 excites
  9. L2:1607 suppresses
  10. L5:138 suppresses
  11. L11:689 excites
  12. L1:20 suppresses
  13. L7:1581 suppresses the last zero in large numbers
  14. L16:75 excites
  15. L16:628 suppresses
  16. L5:779 suppresses
  17. L1:262 suppresses
  18. L3:1169 suppresses
  19. L1:13 excites
  20. L15:2537 suppresses
  21. L0:49 excites
  22. L7:2095 suppresses
  23. L1:1607 excites
  24. L2:1912 suppresses

Feeds later layers

  1. L18:102 strongly excites
  2. L20:174 strongly excites
  3. L19:569 strongly excites
  4. L20:121 strongly suppresses
  5. L18:205 suppresses
  6. L20:413 excites
  7. L20:183 suppresses
  8. L18:474 suppresses
  9. L19:645 suppresses
  10. L22:2749 excites
  11. L19:551 suppresses
  12. L18:198 suppresses
  13. L18:687 suppresses
  14. L23:2938 excites
  15. L21:1072 excites
  16. L18:750 suppresses
  17. L18:249 suppresses
  18. L18:936 suppresses
  19. L18:139 suppresses
  20. L21:921 suppresses
  21. L18:365 suppresses
  22. L18:328 suppresses
  23. L18:405 suppresses
  24. L19:390 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.

2 values between -7.51 and -6.831 values between -4.11 and -3.441 values between -3.44 and -2.761 values between -2.76 and -2.082 values between -2.08 and -1.40379 values between -1.40 and -0.722859 values between -0.72 and -0.04321 values between -0.04 and 0.6466 values between 0.64 and 1.3269 values between 1.32 and 1.9944 values between 1.99 and 2.6745 values between 2.67 and 3.3534 values between 3.35 and 4.0319 values between 4.03 and 4.7116 values between 4.71 and 5.3913 values between 5.39 and 6.077 values between 6.07 and 6.7510 values between 6.75 and 7.422 values between 7.42 and 8.105 values between 8.10 and 8.785 values between 8.78 and 9.462 values between 10.14 and 10.822 values between 11.50 and 12.181 values between 12.85 and 13.531 values between 13.53 and 14.211 values between 18.96 and 19.64offnegativepositiveoften

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. holes
  2. cents
  3. hole
  4. AndGet
  5. pues
  6. speaker
  7. lapse
  8. plane
  9. hyper
  10. synthesize

Suppresses

  1. ользоват
  2. clud
  3. erv
  4. Habit
  5. 皇家
  6. ernel
  7. channelId
  8. 자를
  9. èmes
  10. ecimal