Neuron Explorer

Qwen3-0.6B

unclear: mid-name word pieces

A neuron in layer 8 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 fires on a piece of a longer word or name, such as the middle of 'retainer', 'Renminbi' or 'Beijing-Tianjin-Hebei'. The examples don't share a clear topic, so it is hard to say what it is really for. Turning it up made the model's writing wander without a clear theme.

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

    loose.⏎Because the teeth only can be moved slowly, you'll need to wear braces for about two years. After that you'll need to wear a plastic retainer over your teeth.

  2. #2 peak

    9 cities across China due to severe winter smog. The affected cities, which include the capital Beijing, are located in the regions of Beijing-Tianjin-Hebei and of the northern Yangtze River delta - including the Jiangsu province

  3. #3 peak

    onomy and Epidemiology⏎What do the fields of astronomy and epidemiology have in common? You might think nothing. Those two departments are often not even on the same campus at most universities! However, they have<|endoftext|>By Cliff Ellis⏎The building

  4. #4 peak

    a targeted school. This practice raises the cost of achieving program objectives, such as increased attendance rates, because it provides transfers to many children who would have attended school anyway. Take-home rations programs are

  5. #5 peak

    took place and a new Yuan Renminbi was introduced at a rate of 1 new Yuan to 10,000 old Yuan.⏎The Renminbi in Foreign Exchange⏎During the command economy, the Chinese Yuan Renminbi

  6. #6 peak

    0% of behavioral intention, social norms are rarely even significant and always account for a very small percentage towards the variance of exercise intentions. ...⏎Not exactly what you need?<|endoftext|>Member of the Turkish National Allergy and Clinical Immunology Association. Lect

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 to be careful that I do not make a mistake, but not necessarily the most important one, and even if it is a small part of the work of a person who is not a professional person in a professional field. What is

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

    Perron J, et al. Association between lifestyle habits and adiposity values among children exposed and unexposed to gestational diabetes mellitus in utero. Diabetes Metab Syndr. 2019;13(5):

  2. #2 peak

    the beams. This could lead to problems such as heart or lung damage, or even an increased risk of another cancer later on. Doctors do everything they<|endoftext|>Variety of electromagnetic radiation with frequencies between a few and a few hundred quadrillion oscillations

  3. #3 peak

    is through meticulous and time-consuming detective work that we slowly begin to understand how these ships were built, modified, overhauled and used," Pulak told Live Science."By such means, we try understand the minds of the shipbuilders and their

  4. #4 peak

    bengalensis), a critically endangered species which has lost 99.9 percent of its population due to diclofenac poisoning. Source: Scientific American⏎One of the most important stories in Jane Goodall's book concerns the three

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. L4:1454 excites
  2. L5:133 excites
  3. L5:198 weakly excites unclear: weak "and" in lists
  4. L7:49 weakly suppresses
  5. L7:359 weakly suppresses
  6. L6:1047 weakly suppresses
  7. L7:1549 weakly suppresses
  8. L4:499 weakly excites
  9. L2:781 weakly suppresses 'time' in 'for the first time'
  10. L1:2316 weakly suppresses
  11. L6:1394 weakly suppresses
  12. L4:267 weakly excites
  13. L1:2301 weakly excites
  14. L6:1284 weakly suppresses
  15. L0:1191 weakly excites
  16. L5:158 weakly suppresses
  17. L2:3008 weakly excites
  18. L5:94 weakly suppresses
  19. L1:675 weakly excites
  20. L6:878 weakly suppresses
  21. L7:726 weakly excites
  22. L7:52 weakly excites
  23. L5:46 weakly excites
  24. L1:2430 weakly excites

Feeds later layers

  1. L10:2328 suppresses
  2. L10:2924 suppresses
  3. L19:2878 suppresses
  4. L10:1142 weakly excites
  5. L11:2796 weakly suppresses
  6. L13:1421 weakly excites
  7. L10:2721 weakly suppresses
  8. L9:2186 weakly suppresses
  9. L18:820 weakly excites
  10. L10:1316 weakly excites
  11. L13:852 weakly excites
  12. L10:2036 weakly suppresses
  13. L10:2463 weakly suppresses
  14. L11:1645 weakly excites
  15. L10:1086 weakly excites
  16. L9:1509 weakly excites
  17. L17:2627 weakly excites
  18. L9:1520 weakly excites
  19. L13:1386 weakly excites
  20. L19:894 weakly suppresses
  21. L10:603 weakly suppresses
  22. L11:159 weakly excites
  23. L9:2882 weakly suppresses
  24. L11:1608 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 -4.35 and -4.221 values between -2.61 and -2.491 values between -2.24 and -2.121 values between -1.62 and -1.502 values between -1.50 and -1.371 values between -1.00 and -0.882 values between -0.75 and -0.635 values between -0.63 and -0.5130 values between -0.51 and -0.38146 values between -0.38 and -0.26507 values between -0.26 and -0.131051 values between -0.13 and -0.011222 values between -0.01 and 0.12656 values between 0.12 and 0.24202 values between 0.24 and 0.3668 values between 0.36 and 0.4912 values between 0.49 and 0.61offnegativepositiveoften

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. 两国
  2. 而来
  3. 两地
  4. osto
  5. ソー
  6. gren
  7. .requests
  8. tr
  9. 握手
  10. 請求

Suppresses

  1. iveness
  2. illum
  3. aned
  4. /column
  5. inar
  6. явление
  7. 法宝
  8. liv
  9. onna
  10. cef