Neuron Explorer

Qwen3-0.6B

unclear: weak mid-sentence function words

A neuron in layer 15 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 is weak and hard to read. Its strongest hits are small words such as 'from', 'to', 'but' or 'the' in the middle of a sentence, but the examples have no shared topic. The steering results are mostly repetitive or off-topic, so there is no clear story for what it does.

Written by Claude from this neuron's activations and steering outputs. Confidence: low. 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

    009 International Conference on Alzheimer's Disease (ICAD 2009) in Vienna.⏎"We can't do anything about aging or family history, but research continues to show us that there are lifestyle decisions we all can make to keep

  2. #2 peak

    this article, we will look at five strategies for motivating students and keeping their brains engaged over the summer.⏎Engage in Reading Adventures⏎There is no better time to read than during the dog days of summer. Whether it’s sci-fi, historical

  3. #3 peak

    it quickly! There are a variety of products dedicated specifically to this purpose:⏎While you’re running or working out in general, your body diverts blood flow away from your digestive system because your muscles need improved blood flow and nutrient accessibility during a workout

  4. #4 peak

    of the specific query.The Oracle 9i provides the new functionality of With Clause.The with clause is just like temporary tables in oracle.Mainly the with clause is used to execute subqueries in fast way.It is called as sub-query factoring.⏎

  5. #5 peak

    the beginning.⏎It only consumes constant space.⏎In an imperative language (here Modula-3) the same would be achieved with the following code:⏎TYPE List = REF RECORD next: List; value: INTEGER; END;⏎VAR x := NEW

  6. #6 peak

    ici published in 1700.⏎Its Afrikaans common name, hangertjie, means 'the little hanger', and is thought to come from the way the sunbirds and sugarbirds appear to 'hang' from the flowers

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: I have been reading about the history of the world, and I have been reading about the history of the world, and I have been reading about the history of the world, and I have been reading about the history of the world, and

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

    Step 1: Create a Shortcut⏎Here you have to create a shortcut of your application.⏎Right-click on desktop click on new then click on the shortcut⏎Then you will see one window.⏎Here you have to paste the full path of your

  2. #2 peak

    (Applications > Accessories > Terminal) and navigate to the newly mounted drive. All mounted drives should be in /media, so we’ll use the command⏎and then type the first few letters of our difficult-to-type drive, press tab to auto

  3. #3 peak

    easy as with other programming languages.⏎To create a list of integers, create a new variable and:⏎That’s simple right? And that wasn’t possible with Record Lists.⏎Creating

  4. #4 peak

    paste it at the following path⏎Now open Run (ctrl+R) and type your command name(Here my command name is “DOSBox“) and hit enter, your application will open. Every time you can do that to open

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. L12:2653 excites
  2. L12:1315 excites
  3. L12:208 excites
  4. L12:2888 excites
  5. L14:2863 suppresses
  6. L11:1151 excites
  7. L11:641 excites
  8. L12:271 suppresses
  9. L10:2955 excites
  10. L14:2918 excites
  11. L12:1766 excites
  12. L14:2122 excites
  13. L12:3070 excites
  14. L7:804 weakly suppresses
  15. L13:1700 weakly suppresses
  16. L12:2124 weakly excites
  17. L14:2953 weakly suppresses
  18. L12:1311 weakly suppresses
  19. L12:311 weakly suppresses
  20. L12:822 weakly excites
  21. L13:1334 weakly suppresses
  22. L14:1417 weakly excites
  23. L14:3003 weakly suppresses
  24. L12:2862 weakly excites

Feeds later layers

  1. L16:2971 suppresses
  2. L17:729 suppresses
  3. L20:643 excites
  4. L16:1266 suppresses
  5. L17:1164 excites
  6. L16:1986 excites
  7. L16:1995 suppresses
  8. L16:2788 suppresses
  9. L16:531 excites
  10. L16:3016 excites
  11. L18:2011 suppresses
  12. L16:2016 excites
  13. L16:1233 excites
  14. L17:1033 suppresses
  15. L19:1517 suppresses
  16. L16:814 excites
  17. L17:2405 suppresses
  18. L16:2837 suppresses
  19. L16:2010 weakly suppresses
  20. L16:1311 weakly suppresses
  21. L17:2110 weakly suppresses
  22. L16:2605 weakly suppresses
  23. L16:1882 weakly excites
  24. L24:1239 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.

2 values between -1.25 and -1.181 values between -1.04 and -0.971 values between -0.97 and -0.903 values between -0.90 and -0.832 values between -0.68 and -0.615 values between -0.61 and -0.547 values between -0.54 and -0.477 values between -0.47 and -0.4022 values between -0.40 and -0.3336 values between -0.33 and -0.26105 values between -0.26 and -0.19234 values between -0.19 and -0.12445 values between -0.12 and -0.04963 values between -0.04 and 0.03729 values between 0.03 and 0.10512 values between 0.10 and 0.17373 values between 0.17 and 0.24222 values between 0.24 and 0.31135 values between 0.31 and 0.3866 values between 0.38 and 0.4518 values between 0.45 and 0.527 values between 0.52 and 0.599 values between 0.59 and 0.672 values between 0.67 and 0.741 values between 0.74 and 0.811 values between 1.52 and 1.59offnegativepositiveoften

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. icators
  2. ViewItem
  3. selectedIndex
  4. toFloat
  5. NotFoundException
  6. strikeouts
  7. DatePicker
  8. ketogenic
  9. visually
  10. terminated

Suppresses

  1. ôle
  2. ariat
  3. igar
  4. apologies
  5. earnest
  6. owitz
  7. 接
  8. 装载
  9. Bulk
  10. abler