'for' after verbs like 'fall' or 'click'
A neuronOne of thousands of tiny dials inside each layer. It reads the text so far and produces a number, its activation, that nudges what the model writes next. in layerOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. 4 of Qwen3-0.6B. Its strongest snippets are very consistent: they mostly peak on the same token. It is featuredA neuron picked for the full treatment: steering outputs and a written explanation. About 3,000 of the 86,000 neurons are featured., so it has steering outputs.
What this neuron does
This neuron responds to the word 'for' when it follows a verb, as in 'fallen for', 'stretched for', or 'Click for the answers'. Turning it up did not give clearly related text in the sample outputs.
Written by Claude from this neuron's activations and steering outputs. Confidence: medium. Think it is wrong? Flag it (opens a prefilled issue on GitHub).
Fires most on
The text windows where this neuron's activationThe number a neuron produces for a token. Large positive means it fired hard; negative means it pushed the other way. was highest. Amber marks positive activation; the outlined tokenA piece of text the model reads at once: often a word, sometimes part of a word or a punctuation mark. is the peak. Hover a token for its strength.
-
fossil that definitively prove their hunch, and are able to reveal the precise statistics of the giant herbivore. It seems that the beast would have stretched for 20 meters
-
PDF [portable document format] printable page. (If you are unable to view the printable page, download the free Adobe Acrobat Reader.)⏎Click for the answers to this week's puzzle.⏎Click for Sudoku Puzzles from previous
-
then hawking their services as conduits to the afterlife to the credulous grieving public commonly used. (Can you imagine anyone being foolish enough to fall for such predatory charlatanry today?)⏎That turn in
-
itself as Bodoland Martyrs Cemetery. Inside the Martyrs Cemetery, several hundred blocks of black granite are inscribed with names and addresses of men who have fallen for Bodoland. Life-size granite statues of leaders of the Bodo movement and insurgency
-
They have been sunk into E. plukenetii and are recognized as subsp. pl<|endoftext|>| ||Minding Your Mind || |⏎When Striving for Perfection Is a Problem⏎Last Reviewed by Faculty of Harvard Medical School on May
-
family members and government officials to change the trajectory of Alzheimer's disease," concluded Geiger.⏎The research was slated for presentation Monday at the Alzheimer's Association International Conference in Paris. Research presented at medical
SteeringAdding a push along a neuron while the model writes, to see how its output changes. Turning it up or down.
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.
Here is something I have been thinking about lately: I am a new user. Please don't use the general public. This is a personal website. I need to be a CEO, a CTO, a CTO, and a CTO. This is a CEO, a CTO
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
some easy and age-appropriate science fair project ideas for kids that will keep your kid excited about learning.⏎1. Lava Lamp⏎Image Credit: funlearningforkids.com⏎With this project, you and
-
the Malian military from the north, however, the separatist forces soon became embroiled in a conflict of their own, between the original Mouvement National pour la Libération de l’
-
waste specialist consultancy, Eunomia, who confirm the credibility of APEAL’s methodology and data.⏎www.apeal.org and www.steelforpackaging.org<|endoftext|>Paint Analysis - Peeling Paint? How to Diagnose
-
these prepositions must be in accusative case: durch-throughfuer-for gegen-againstohne-without um-around Er kauft das Geschenk fuer mich.<|endoftext|>In case you are searching for easy Preschool Activities, you can
Connections
Show on mapWhich neuronsOne of thousands of tiny dials inside each layer. It reads the text so far and produces a number, its activation, that nudges what the model writes next. in earlier layersOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. feed this one, and which later ones it feeds. Amber links excite, blue links suppress; longer bars are stronger.
Fed by earlier layers
- L3:381 excites 'for' in research institute names
- L1:1341 suppresses
- L2:75 weakly suppresses
- L0:1543 weakly excites
- L2:2328 weakly suppresses
- L3:1390 weakly excites 'that' in 'so that' purpose clauses
- L2:1860 weakly excites
- L3:691 weakly excites
- L0:2711 weakly suppresses
- L1:1464 weakly excites
- L2:41 weakly suppresses
- L2:49 weakly suppresses
- L2:549 weakly suppresses
- L2:190 weakly suppresses
- L1:1972 weakly suppresses
- L3:456 weakly suppresses
- L0:4 weakly suppresses
- L3:2766 weakly excites
- L3:464 weakly excites
- L3:2818 weakly excites
- L3:1164 weakly excites
- L1:1306 weakly excites
- L0:1301 weakly suppresses
- L2:527 weakly excites
Feeds later layers
- L9:2587 suppresses
- L17:1223 suppresses
- L19:1221 suppresses
- L5:1090 suppresses
- L16:2336 suppresses
- L9:1890 suppresses
- L10:132 suppresses
- L5:763 suppresses
- L7:1172 suppresses 'for' after past participles like selected
- L17:2949 suppresses 'for' introducing an example or reason
- L10:1029 suppresses
- L9:1550 suppresses 'to' after 'matters' or 'means' phrases
- L16:524 suppresses
- L21:2012 suppresses "to" before an infinitive or noun
- L5:2538 suppresses
- L17:697 suppresses
- L12:2212 suppresses 'to' or 'for' opening a purpose phrase
- L10:2412 weakly suppresses
- L6:2899 weakly suppresses
- L15:2573 weakly suppresses
- L17:2302 weakly suppresses 'in' after a noun
- L17:2527 weakly suppresses
- L5:892 weakly suppresses
- L5:1864 weakly suppresses
Activation histogramA chart of how often a neuron takes each activation value.
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.
Logit lensReading which output tokens a neuron pushes toward or away from, straight off its output weights, before the later layers have their say.
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 layersOne step in the stack the text passes through. Qwen3-0.6B has 28 layers, each with 3,072 neurons. instead.
Promotes
- 都会
- ammed
- auses
- 都会有
- 还是会
- 会在
- istediği
- 会有
- 会
- ernet
Suppresses
- bidden
- HCI
- lox
- .getColumnIndex
- @student
- دا
- lix
- @show
- blister
- bind