Neuron Explorer

Qwen3-0.6B

unclear: product and model names

A neuron in layer 10 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

It fires on the piece of a product or model name that comes right before its version number, such as the dash in MiG-15 or the word after Arduino. Its strongest negative hits are in plain tech wording like "template engine" or "spell check program". Turning it up gave rambling text with no 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

    language. Octave has extensive tools for solving common numerical linear algebra problems, finding the roots of nonlinear equations, functions written in Octave's own language, or by using dynamically loaded modules written in C, C++, Fortran,

  2. #2 peak

    ouflaged MiG-15bis, serial number 2315393 (3

  3. #3 peak

    parts — a modular system developed back in the early 1950s.⏎At the heart of the machine lies a Raspberry Pi Compute Module along with Arduino Mini. The Compute Module actuates a series of motors and grippers, while also

  4. #4 peak

    that the haplotypes of the sequenced SARS-CoV-2 viruses were diverse and changed over time, but that the percentage of infected participants

  5. #5 peak

    North Atlantic air traffic. Then a young scientist working for the federal government, she’d been assigned the task following a near-miss incident involving a KLM Boeing 747, which had flown into an ash cloud over Alaska and lost all

  6. #6 peak

    race relations during the 1960s are important parts of each other’s histories. To the region’s most ardent segregationists, the Douglas DC-4s and Lockheed Electras landing from faraway cities on shimmering southern run

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 would like to use a matrix to manage the project, and I need to include a task manager, and I need to include a risk management tool. The task manager, such as Jira, and the risk management tool, such as

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

    grow in complexity with time.⏎The global pattern to follow is MVC and the layering:⏎(View & Controller)⏎|View||HTML templates usually generated using a template engine|⏎|Input Controller||Filter and validate data|⏎||Application Controller||Application flow

  2. #2 peak

    the most widely used server-side scripting language⏎At time of this writing, PHP is the most used server-side language (

  3. #3 peak

    , particularly if you’re applying for college credit or other kinds of credit. You do not want your newspaper to appear grammatically challenged, therefore use a spell check program to be certain everything is correct. It may seem small, however this can be

  4. #4 peak

    . While some people consider this changes as something bad paying attention to the fact that such mass distribution deprives new albums and songs their value, the others believe that streaming helps to fight the piracy which exploded in the early 2000s

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. L9:379 suppresses
  2. L5:1480 excites
  3. L9:1024 excites
  4. L8:391 suppresses
  5. L6:878 weakly excites
  6. L9:2959 weakly excites
  7. L9:1270 weakly excites
  8. L9:2346 weakly suppresses
  9. L9:1873 weakly excites
  10. L6:1506 weakly excites
  11. L9:1933 weakly excites
  12. L1:1910 weakly excites
  13. L7:1737 weakly suppresses
  14. L6:2759 weakly excites
  15. L8:1925 weakly excites
  16. L5:489 weakly excites
  17. L8:1307 weakly suppresses words for stretching out or extending
  18. L4:2018 weakly suppresses
  19. L7:2805 weakly suppresses
  20. L4:2096 weakly excites
  21. L8:2577 weakly suppresses
  22. L0:2377 weakly suppresses
  23. L8:2765 weakly excites
  24. L1:157 weakly suppresses

Feeds later layers

  1. L12:2096 suppresses
  2. L12:1184 excites
  3. L13:2227 suppresses
  4. L21:1476 suppresses
  5. L16:2057 suppresses
  6. L12:2314 suppresses
  7. L13:2520 suppresses
  8. L11:1766 suppresses
  9. L11:1190 suppresses
  10. L14:2069 excites
  11. L11:1385 suppresses
  12. L11:1937 excites
  13. L13:2000 suppresses
  14. L13:1546 suppresses
  15. L18:1931 suppresses
  16. L13:327 suppresses
  17. L13:1257 suppresses
  18. L18:2768 suppresses
  19. L16:2367 suppresses
  20. L13:809 suppresses
  21. L11:1221 weakly suppresses
  22. L11:1500 weakly excites
  23. L11:2525 weakly suppresses
  24. L13:2839 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 -3.09 and -2.961 values between -2.57 and -2.441 values between -1.91 and -1.782 values between -1.65 and -1.522 values between -1.52 and -1.395 values between -1.39 and -1.261 values between -1.26 and -1.138 values between -1.13 and -1.008 values between -1.00 and -0.8713 values between -0.87 and -0.745 values between -0.74 and -0.6113 values between -0.61 and -0.4840 values between -0.48 and -0.35157 values between -0.35 and -0.22501 values between -0.22 and -0.091370 values between -0.09 and 0.041088 values between 0.04 and 0.17511 values between 0.17 and 0.30142 values between 0.30 and 0.4326 values between 0.43 and 0.563 values between 0.56 and 0.693 values between 0.69 and 0.821 values between 0.95 and 1.082 values between 1.08 and 1.211 values between 1.34 and 1.471 values between 1.60 and 1.731 values between 2.00 and 2.13offnegativepositiveoften

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. phem
  2. бот
  3. neau
  4. \Blueprint
  5. ture
  6. อน
  7. SPATH
  8. ろ
  9. umph
  10. uario

Suppresses

  1. providers
  2. provider
  3. companies
  4. _provider
  5. achi
  6. _PROVIDER
  7. provider
  8. breaches
  9. providers
  10. 公司