'et' in 'et al.' citations
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. 12 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 lights up on the word 'et' in academic citations like 'Smith et al.', where the next word is predicted to be 'al.'. Turning it up did not make the writing about citations.
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.
-
influence of aerosols on the global climate.⏎Ault, A.P., et al. “Raman Microspectroscopy and Vibrational Sum Frequency Generation Spect
-
promising approach to prevent deteriorated adiposity values among this high-risk population,” the researchers wrote.⏎Bélanger M, Dugar C, Perron J, et al. Association between lifestyle habits and adiposity values among children exposed and unex
-
marked ecological changes, including alterations to climatic regimes, phenology, resource availability and habitat quality (Zhou et al. 2004; Grimm et al. 2008). Consequently, growth in urban development is a
-
ious complications are uncommon.⏎Broaddus VC, Light RW. Pleural effusion. In: Mason RJ, Murray JF, Broaddus VC, et al., eds. Murray and Nadel's Textbook of Respiratory Medicine.
-
fever. The effect on mastoidectomy is unclear, but a clinically important increase seems unlikely. (Level of Evidence: 2c)⏎Sharland M, et al. Antibiotic prescribing in general practice and hospital admissions for peritonsill
-
ators through competition, and maintenance of a functional balance of biodiversity in the local community (Krebs et al., 1995; Terborgh et al., 1999; Logan & Sweanor, 2
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: the information I have been given, the information I have been given, and the information that is in the food I have been told, in the food I have been told, or the food I have been told, or the food I have
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
risk for wandering astronauts, he adds, but there would be time to return to a shielded base.⏎To continue reading this article, subscribe to receive access to all of newscientist.com, including 20 years of archive content.<|endoftext|>
-
replace human translation. Neither BioOne nor the owners and publishers of the content make, and they explicitly disclaim, any express or implied representations or warranties of any kind, including, without limitation, representations and warranties as to the functionality of the translation
-
Look-up table method⏎Create Volcano (or Atoll) martix. It is an extension of Bullseye matrix problem.⏎Who has power to do everything in this world?⏎Close MATLAB with keyboard⏎Find the treasures in MATLAB Central and
-
will take you to the Copyright Clearance Center’s RightsLink service. You will be able to get a quick price and instant permission to reuse the content in many different ways.<|endoftext|>- Major Systems >⏎- The Plumbing Rough-In⏎The Plumbing Rough-In
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
- L4:543 suppresses
- L10:2724 excites
- L9:1539 excites
- L6:2654 suppresses
- L7:727 excites
- L3:990 excites
- L11:240 weakly excites
- L10:157 weakly suppresses end of document and web boilerplate
- L1:2695 weakly excites
- L7:755 weakly suppresses
- L6:1175 weakly suppresses
- L9:751 weakly suppresses
- L5:1552 weakly suppresses
- L11:607 weakly excites
- L11:1785 weakly suppresses
- L8:1455 weakly suppresses
- L10:183 weakly suppresses
- L6:390 weakly suppresses
- L6:2811 weakly excites
- L6:1868 weakly excites
- L11:2667 weakly excites
- L4:1529 weakly excites
- L2:2673 weakly excites
- L0:2594 weakly excites
Feeds later layers
- L15:1740 excites
- L15:2148 weakly excites
- L14:1263 weakly excites
- L13:1419 weakly excites
- L13:1118 weakly excites
- L16:1127 weakly suppresses opening bracket after an imperial measurement
- L18:1811 weakly excites 'and' linking two descriptive claims
- L16:3039 weakly excites
- L21:2438 weakly suppresses
- L26:1448 weakly suppresses
- L14:1738 weakly excites
- L21:593 weakly excites
- L15:1930 weakly excites
- L14:628 weakly excites end of document boundary token
- L21:441 weakly excites
- L15:541 weakly excites
- L23:792 weakly suppresses
- L14:3001 weakly excites
- L20:1938 weakly suppresses
- L14:362 weakly excites
- L19:1713 weakly excites
- L15:178 weakly excites
- L18:2722 weakly excites
- L16:486 weakly excites
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
- Emin
- GMEM
- .CreateCommand
- 之意
- thereof
- Kensington
- Words
- 五大
- 亿美元
- ants
Suppresses
- rier
- bral
- heiro
- 笼
- >"+⏎
- _ENTER
- plementary
- 嗓子
- tero
- ><![