stem cell terms in biology text
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. 8 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 words 'stem' and 'self-renew' when they appear in articles about stem cells and cancer. When it was turned up, the written text drifted to unrelated topics, so the steering results don't show a clear effect.
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.
-
is deregulated in many types of human malignancies, including cancers of kidney, liver, stomach, breast, and brain. Normally, only stem cells and progenitor cells express MET, which allows these cells to grow invasively in order to
-
, and hydrangea. Rejuvenation pruning is best done in late winter or early spring.<|endoftext|>Neural stem cells (NSCs) can self-renew and differentiate into neurons and glia. Transplanted NS
-
of U.S. scientists has identified phosphorylated signalling proteins in human embryonic stem cells (hESCs) studying which may help understand the mechanisms that determine whether stem cells divide or differentiate
-
was poorly understood.⏎According to them, identification of these phosphorylation sites provides insights into known and novel hESC signalling pathways and highlights signalling mechanisms that influence self-renewal and differentiation.⏎"This research will be a big boost for stem cell scientists.
-
over remarkably long distances, and glia. Grafts of cultured human NSCs expressing GFP resulted in similar findings. Thus, methods are defined for improving neural stem cell grafting, survival and analysis of in vivo findings.⏎21 Related Jo
-
genetics at Harvard Medical School (HMS). "It also shows, from one lung cancer to another, the cancer stem cells are not the same."⏎Cancer stem cells are a subset of cancer cells believed to elude conventional treatments and eventually regenerate
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: which is the way to spread this, so 100 is the coefficient to be used when no decimal is involved. The formula used in this case, which is to be used when no decimal is present, so the formula for
Most negative on
Where the activation went furthest below zero. Blue marks negative activation. Many neurons mean something different in each direction.
-
only music production and records selling, but also touring and merchandising. Artists themselves are looking for new ways to make money,
-
his songs always contain the words ‘Guruguha’ towards the end.⏎In his late life, he toured South India extensively and composed songs on the various deities of the religious pantheon
-
computer science teacher Myra Deister of Sunny Hills High in Fullerton didn’t learn computer programming in high school.⏎Neither did most of the professionals who come to speak to her classes about their careers. Across the country, just 10 percent
-
with the procedure now correctly termed Mohs Micrographic Surgery.⏎After the removal of the visible portion of the tumor by excision or curettage (debulking), there are two basic steps to each Mohs Micrographic Surgery stage. First
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
- L7:2267 suppresses
- L6:1916 weakly excites "stem" in stem cell phrases
- L5:1395 weakly excites
- L4:2759 weakly excites
- L4:2988 weakly excites
- L0:2539 weakly suppresses
- L4:1053 weakly excites
- L6:1924 weakly suppresses
- L7:63 weakly excites
- L4:1050 weakly excites
- L4:3038 weakly excites
- L3:2428 weakly suppresses
- L2:1688 weakly suppresses 'off of' and 'of' after 'off'
- L4:2645 weakly suppresses
- L0:2137 weakly excites
- L7:2185 weakly excites
- L6:2411 weakly suppresses
- L6:1142 weakly excites
- L7:191 weakly excites
- L7:2149 weakly suppresses
- L7:1838 weakly excites
- L7:49 weakly suppresses
- L0:106 weakly suppresses unclear: 'if' opening a statement, 'local'
- L1:1462 weakly excites
Feeds later layers
- L10:1312 excites
- L9:0 excites
- L9:1413 weakly excites
- L20:2606 weakly excites
- L22:2886 weakly excites
- L11:1519 weakly excites
- L10:1064 weakly excites
- L16:845 weakly excites
- L9:2292 weakly excites
- L9:1553 weakly excites
- L20:2878 weakly excites
- L19:2442 weakly excites
- L9:1679 weakly suppresses
- L11:666 weakly excites
- L19:387 weakly suppresses
- L22:1521 weakly excites
- L9:357 weakly excites
- L10:623 weakly excites
- L16:2931 weakly excites "all" meaning every level or group
- L12:1227 weakly excites
- L25:2064 weakly excites
- L24:1810 weakly suppresses
- L13:3009 weakly suppresses
- L11:906 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
- subclass
- omorphic
- .imgur
- 细胞
- .createCell
- filtr
- subclass
- feb
- _cells
- 층
Suppresses
- ounds
- linky
- laces
- Scandinavian
- Unknown
- 隍
- igator
- Unknown
- undisclosed
- 地