© 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. 357
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     reck
    -0.11
    endon
    -0.10
     jadx
    -0.10
     〃
    -0.10
    arios
    -0.10
    跡
    -0.10
    ุบ
    -0.10
     Cly
    -0.10
    ultan
    -0.10
    /angular
    -0.10
    zas
    -0.10
     unreal
    -0.09
    ogi
    -0.09
    725
    -0.09
    /weather
    -0.09
     dend
    -0.09
    Tho
    -0.09
    reck
    -0.09
    deniz
    -0.09
    ocrates
    -0.09
    Positive Logits
     Scrolls
    0.10
     Zot
    0.10
     Haw
    0.09
     Sawyer
    0.09
     Trick
    0.09
    oints
    0.09
    .googleapis
    0.09
     spear
    0.09
    ings
    0.09
     �
    0.09
     Sentry
    0.09
    onian
    0.09
    oy
    0.09
    cole
    0.08
    coli
    0.08
    �
    0.08
     AC
    0.08
    INGS
    0.08
    ��
    0.08
     NSF
    0.08
    Activations Density 46.347%
    Loading dashboard...