Neuron Explorer

Qwen3-0.6B

unclear: 'lesson' and 'lique' word pieces

A neuron in layer 2 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 seems to fire on the start of words like 'Lessons' and 'liquefied', and on pieces of technical words. The examples do not share a clear theme, so the pattern is uncertain. Turning it up produced rambling text about temperatures and sums.

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

    energy needs. For the majority of off-grid operations, this means a choice between oil, LPG (liquefied petroleum gas) or LNG (liquefied natural gas) for high

  2. #2 peak

    of the UNLIKE.⏎Sir M. FOSTER, K.C. B., M. D., and LEWIS E. SHOKÉ,⏎LESSONS IN ELEMENTARY PHY-⏎PHYSIOLOGY. By Sir MICHAEL F

  3. #3 peak

    , the institution of Marriage — and how these wrong decisions can be avoided and remedied. Sign up now while there is still space in this special course!⏎Lessons cover issues such as the acknowledgment of God, Marriage, Life, Obscenity

  4. #4 peak

    (non-polarized), inexpensive, and durable. Avoid capacitors with any kind of polarity marking, as these will be destroyed when powered by AC!⏎Lessons In Electric Circuits, Volume 2, chapter 1: "Basic AC

  5. #5 peak

    the Arduino. It can be found here at arduino.cc for Mac, Linux, and PC.⏎One cannot play the Can Can without finesse!<|endoftext|>Lessons From the Past The following i⏎The following is an excerpt from the recommended standards

  6. #6 peak

    0 seconds of the French folksong "Au Clair De La Lune" on April 9, 1860.⏎Édouard-Léon Scott de Martinville recorded the voice by using a "phonautograph" to

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: the fact that the patient has been. I am the patient. I am the patient. I am the patient. I am the patient. I am the patient. I am the patient. I am the patient. I am the patient.

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

    why: Doing so stimulates the brain the same way sex, food, and cash do. Researchers scanned subjects' brains and found that parts linked to those pleasures lit up when subjects chatted about themselves.⏎Researchers also offered study subjects up to 4

  2. #2 peak

    BC to AD 500, consisting of thousands of large stone jars placed on hills within the central plain of the Xiangkhoang Plateau in Laos.⏎According to local Lao legend, the jars were created by a race of

  3. #3 peak

    180 - 197.⏎Kwong-loi Shun (1997). Mencius and Early Chinese Thought.

  4. #4 peak

    :⏎Unit Objectives: At the completion of this unit the⏎Chapter Fifteen Summary⏎The police frequently use three procedures to help by witnesses identify criminals: lineups, show-up, and photographic lineups. Lineups involve showing the witness a

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. L1:2755 weakly suppresses
  2. L1:1899 weakly excites
  3. L0:1934 weakly suppresses
  4. L1:1298 weakly suppresses
  5. L1:1659 weakly excites
  6. L1:1870 weakly suppresses
  7. L1:3038 weakly excites
  8. L1:1583 weakly excites
  9. L1:1099 weakly excites
  10. L0:432 weakly excites
  11. L1:1973 weakly suppresses
  12. L0:1123 weakly suppresses
  13. L0:178 weakly suppresses
  14. L0:2787 weakly excites
  15. L1:2506 weakly excites
  16. L0:3058 weakly excites
  17. L0:1224 weakly suppresses
  18. L0:1301 weakly suppresses
  19. L0:1644 weakly suppresses
  20. L0:960 weakly suppresses
  21. L1:1953 weakly suppresses
  22. L0:53 weakly excites
  23. L1:2330 weakly suppresses
  24. L0:42 weakly excites

Feeds later layers

  1. L21:252 excites
  2. L5:1294 excites
  3. L18:198 excites
  4. L19:593 excites
  5. L26:2235 weakly excites word-start 'l' after a space
  6. L10:904 weakly suppresses
  7. L3:1929 weakly suppresses
  8. L16:671 weakly excites
  9. L18:331 weakly excites
  10. L3:2309 weakly suppresses
  11. L27:1748 weakly suppresses
  12. L5:2321 weakly excites
  13. L4:2870 weakly excites
  14. L21:2568 weakly excites
  15. L3:2040 weakly excites
  16. L3:1036 weakly suppresses
  17. L27:1934 weakly suppresses
  18. L24:2459 weakly suppresses
  19. L26:2668 weakly excites
  20. L4:1762 weakly excites "this" in time and context phrases
  21. L3:2216 weakly excites
  22. L5:1093 weakly excites
  23. L10:273 weakly excites
  24. L6:2766 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 -1.29 and -1.201 values between -1.12 and -1.033 values between -0.61 and -0.521 values between -0.52 and -0.444 values between -0.44 and -0.3530 values between -0.35 and -0.27124 values between -0.27 and -0.18530 values between -0.18 and -0.101357 values between -0.10 and -0.011326 values between -0.01 and 0.08380 values between 0.08 and 0.16107 values between 0.16 and 0.2521 values between 0.25 and 0.335 values between 0.33 and 0.424 values between 0.42 and 0.503 values between 0.50 and 0.591 values between 0.59 and 0.672 values between 0.76 and 0.842 values between 1.01 and 1.102 values between 1.10 and 1.181 values between 1.18 and 1.271 values between 1.35 and 1.441 values between 1.44 and 1.521 values between 2.04 and 2.12offnegativepositiveoften

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. ={$
  2. absorbs
  3. cope
  4. ═
  5. TEE
  6. WC
  7. راق
  8. >{$
  9. parole
  10. ousel

Suppresses

  1. elman
  2. roud
  3. azz
  4. builders
  5. rawing
  6. .styleable
  7. 'B
  8. LOGGER
  9. 募集
  10. DrawerToggle