mid-sentence words in web boilerplate
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. 19 of Qwen3-0.6B. Its strongest snippets are fairly consistent: several of them 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 fires on ordinary words in the middle of a sentence, such as 'or', 'is' and 'indicates', most often in book-site or paywall boilerplate like 'download or read it online'. It turned negative on words like 'see' and 'print' in access notices. The steering results did not show a clear theme, so its job is hard to pin down.
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 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.
-
stanz. The team of scientists headed by...⏎Yersiniae cause severe intestinal infections. Studies using Yersinia pseudotuberculosis as a model organism aim to elucidate the infection mechanisms of these...⏎Researchers from the
-
24 years old on Friday April 5th in 1974. On what day⏎of the week was she born?⏎A tetromino is made up of four squares joined edge to edge. Can⏎this tetrom<|endoftext|>
-
?⏎Based on our data, we think this problem is relevant for Professor Finnegan's class at WSU.⏎What textbook is this problem found in?⏎Our data indicates that this problem or a close variation was asked in Chemistry: An Atoms First
-
measured unless subject to both ethical and commercial consideration.⏎Home page url⏎Download or read it online for free here:⏎by Flora Klickmann - G.
-
Major Characters Chapter Four: Complete Summary Chapter Five: Critical Analysis⏎To view this DRM protected ebook on your desktop or laptop you will need to have Adobe Digital Editions installed. It is a free
-
Physiology in Health and Illness 12e⏎Goodreads helps you keep track of books you want to read. Want to Read saving…. Want to Read Currently Reading Read. Other editions. Enlarge cover. Error rating book.⏎Browse more
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 have to be a man in a * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * * *
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
status as electors in August 1920 by the Nineteenth Amendment to the federal Constitution, the...⏎Users without a subscription are not able to see the full⏎to access all content.<|endoftext|>Great Slaty becomes World's
-
able solution for polygonal transects remains elusive.⏎Keywords: Boundary overlap, Inclusion region, Reflection method, Transect configuration⏎- We recommend that you also print this page and attach it to the printout of the article
-
2007. The result is encouraging. The model provides an objective basis for the development of acid rain forecasting operation in the province.⏎This is a preview of subscription content
-
.25 new (22% off) $21.95 direct from Amazon Amazon page|⏎Setup an account with your affiliations in order to access resources via your University's proxy server⏎Configure custom proxy (use this if your
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
- L11:29 excites
- L18:396 suppresses
- L16:1543 suppresses
- L11:17 suppresses
- L16:248 excites
- L15:1317 excites
- L18:1077 excites
- L17:892 suppresses
- L10:61 suppresses
- L10:46 suppresses
- L0:2643 weakly suppresses
- L18:218 weakly excites
- L7:22 weakly suppresses
- L12:1115 weakly excites
- L10:124 weakly suppresses
- L16:132 weakly suppresses
- L15:1135 weakly excites
- L18:819 weakly excites
- L1:491 weakly excites
- L15:23 weakly suppresses
- L16:314 weakly excites
- L11:349 weakly excites 'of' or 'for' linking a place or group
- L10:333 weakly excites
- L17:682 weakly excites
Feeds later layers
- L26:1082 excites
- L20:543 suppresses
- L27:2134 weakly excites
- L24:1707 weakly excites
- L22:157 weakly suppresses
- L25:1914 weakly excites
- L22:304 weakly suppresses
- L21:81 weakly suppresses
- L24:1047 weakly excites
- L25:913 weakly excites
- L26:1653 weakly suppresses
- L25:1890 weakly excites
- L25:1668 weakly excites
- L25:741 weakly excites
- L20:1232 weakly suppresses
- L23:1886 weakly excites
- L20:71 weakly excites
- L25:440 weakly excites
- L22:108 weakly suppresses
- L27:990 weakly excites
- L20:128 weakly suppresses
- L22:1894 weakly excites
- L20:1719 weakly suppresses
- L25:2069 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
- $b
- =query
- $max
- =value
- (vs
- :b
- 棣
- losion
- bles
- ном
Suppresses
- rop
- ro
- board
- ạnh
- Britann
- 要
- api
- Sole
- fo
- тя