Neuron Explorer

Qwen3-0.6B

'to' after a noun or verb of motion

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 "to" when it comes right after a noun or verb that is followed by an infinitive, such as "helicopter to scope" or "going from failure to failure". Turned up, the model's replies drifted into odd, unrelated topics.

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

    agricultural workers what realities of their lives you found most disturbing about their working conditions. Please be specific and cite your source.Please identify two reasons agricultural workers leave their homeland to work in the fields of American agricultural for low pay. Is it possible that free

  2. #2 peak

    ) Before humans make it to Mars, NASA will send a helicopter to scope out the terrain.⏎The solar-powered Mars Helicopter will be safely stowed

  3. #3 peak

    as Pyrrhus the Delian fisherman, and then Pythagoras.There is a famous story<|endoftext|>Have you ever gone through the harrowing experience of going to grab some milk, wanting to know how much was

  4. #4 peak

    worry about failure.⏎31. A true friend is one who overlooks your failures and tolerates your success!⏎32. Success consists of going from failure to failure without

  5. #5 peak

    both rescue the continuity and advance the scientific capability of the mission, if it reaches orbit. If it doesn’t, it won’t be the first Landsat satellite to fail.⏎In 1993, Landsat 6 didn’t make

  6. #6 peak

    of it as time-released success.⏎21. There are no failures. Just experiences and your reactions to them.⏎22. Courage is going from failure to failure without losing enthusiasm.⏎23. Failure is unimportant. It takes courage

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 only way to make it work, if it was a problem that was fixed by the problem of the other’s problems. Which of the following is the most likely best friend for a problem problem problem? A) someone who is the only

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

    beekeepers use. However, the bees usually win out. Once the queen cells are eliminated the bees will produce more queen celIs.⏎|Prepared by:||Gordon Rudloff⏎Ohio Department of Agriculture<|endoftext|>Logic & ProofsOpen Learning

  2. #2 peak

    crosses directly through the desert with the Great Bitter Lake bein part of the canal. In the background the Sinai Peninsula and the Red Sea.⏎|View:||The Suez Canal|<|endoftext|>Old Times literature essays are academic essays for citation.

  3. #3 peak

    grow effectively in water:-⏎Ways to care for Monstera and make them grow faster:-⏎The Monsteras are widely growing plant types. They have a lot of ways to

  4. #4 peak

    as under :- 1. Introduction :- Mediation introduces the parties, explains mediation process, establishes neutrality and eventually generates momentum towards settlement. 2. Joint Session :- Mediation gathers information about the factual background and interests of the parties. Establishes

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. L14:348 suppresses
  2. L10:33 suppresses
  3. L9:7 excites
  4. L11:18 excites
  5. L15:44 suppresses
  6. L5:5 suppresses digit after a label like paper or type
  7. L11:31 suppresses
  8. L13:132 excites "of" after a noun
  9. L16:170 suppresses
  10. L14:51 excites colon that introduces a statement
  11. L15:123 suppresses
  12. L14:917 excites
  13. L14:303 excites
  14. L3:3 suppresses
  15. L1:1 excites
  16. L16:215 suppresses
  17. L13:1046 suppresses 'in' or 'on' ending a phrase
  18. L12:5 excites
  19. L14:251 suppresses
  20. L6:4 suppresses
  21. L16:337 excites
  22. L16:1596 suppresses
  23. L1:8 excites
  24. L15:798 weakly excites

Feeds later layers

  1. L19:315 suppresses
  2. L19:926 suppresses
  3. L19:380 suppresses
  4. L21:122 suppresses
  5. L18:655 suppresses
  6. L20:129 suppresses
  7. L18:777 suppresses
  8. L20:247 suppresses
  9. L19:183 suppresses
  10. L18:467 suppresses
  11. L18:459 suppresses
  12. L20:463 suppresses
  13. L19:402 suppresses
  14. L20:133 suppresses
  15. L18:2498 suppresses
  16. L18:285 suppresses
  17. L20:190 suppresses
  18. L20:119 suppresses
  19. L19:308 weakly suppresses
  20. L18:1186 weakly suppresses
  21. L25:535 weakly excites commas inside number lists
  22. L19:283 weakly suppresses
  23. L20:197 weakly suppresses
  24. L19:243 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 -6.35 and -5.961 values between -5.96 and -5.561 values between -4.38 and -3.992 values between -3.99 and -3.592 values between -3.59 and -3.203 values between -3.20 and -2.8012 values between -2.80 and -2.4113 values between -2.41 and -2.0115 values between -2.01 and -1.6232 values between -1.62 and -1.2364 values between -1.23 and -0.83115 values between -0.83 and -0.44415 values between -0.44 and -0.041440 values between -0.04 and 0.35647 values between 0.35 and 0.75266 values between 0.75 and 1.14220 values between 1.14 and 1.54167 values between 1.54 and 1.93151 values between 1.93 and 2.32103 values between 2.32 and 2.7282 values between 2.72 and 3.1155 values between 3.11 and 3.5135 values between 3.51 and 3.9028 values between 3.90 and 4.3016 values between 4.30 and 4.696 values between 4.69 and 5.086 values between 5.08 and 5.483 values between 5.48 and 5.871 values between 5.87 and 6.271 values between 6.27 and 6.663 values between 6.66 and 7.061 values between 8.24 and 8.631 values between 9.03 and 9.42offnegativepositiveoften

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. チョ
  2. 俟
  3. dden
  4. ellij
  5. mö
  6. ivirus
  7. @end
  8. spd
  9. झ
  10. .idea

Suppresses

  1. igrams
  2. ang
  3. ⏎⏎⏎
  4. ather
  5. ⏎ ⏎
  6. -grand
  7. omb
  8. ⏎
  9. itr
  10. ⏎⏎