© 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. 428
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    茂
    -0.12
    надлеж
    -0.11
    ALSE
    -0.11
    езульт
    -0.10
    BCM
    -0.10
     metic
    -0.10
    ，存于
    -0.10
    ertia
    -0.10
     prot
    -0.10
    ldkf
    -0.10
    Ordinal
    -0.10
    parms
    -0.10
    allee
    -0.10
    lemn
    -0.10
     unofficial
    -0.10
     Franken
    -0.10
     �
    -0.10
    ColumnsMode
    -0.10
     lar
    -0.10
    hood
    -0.10
    Positive Logits
    amin
    0.11
    .Load
    0.11
     whites
    0.10
     Bes
    0.10
    *
    0.10
    .toolbox
    0.10
     disg
    0.09
    ανά
    0.09
     sight
    0.09
     advent
    0.09
    Abs
    0.09
    щими
    0.09
    pd
    0.09
     Kenn
    0.09
    ​
    0.09
     Advisory
    0.09
     Indo
    0.09
    anda
    0.09
    　ﾉ
    0.09
     expelled
    0.08
    Activations Density 44.967%
    Loading dashboard...