© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Neuronpedia · MLP Neurons
    5. Llama3.3-70B-IT
    7. MLP Neurons - Layer 21
    9. 496
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    aji
    -0.12
     Jam
    -0.11
     ab
    -0.10
     CDC
    -0.09
    plication
    -0.09
     득
    -0.09
    orus
    -0.09
    济
    -0.09
    389
    -0.09
     Ange
    -0.09
    uden
    -0.09
    opsis
    -0.09
     RSS
    -0.09
     Zodiac
    -0.09
     Fury
    -0.09
    ⠀
    -0.08
    onavir
    -0.08
    AGER
    -0.08
    ieri
    -0.08
    ภาค
    -0.08
    Positive Logits
    ppt
    0.10
    uka
    0.10
    wick
    0.10
    959
    0.10
    serter
    0.10
    orning
    0.10
    dí
    0.09
     Hlav
    0.09
     Pruitt
    0.09
     ambassador
    0.09
     border
    0.09
    AST
    0.09
    �
    0.09
    šak
    0.09
    402
    0.09
     slap
    0.09
     Coleman
    0.09
    ScrollIndicator
    0.09
    gif
    0.08
    nbsp
    0.08
    Activations Density 58.021%
    Loading dashboard...