© 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. 395
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ean
    -0.11
     CL
    -0.10
    CL
    -0.10
    iss
    -0.10
    mast
    -0.09
    СО
    -0.09
     nonatomic
    -0.09
     soy
    -0.09
     butt
    -0.09
     Clarence
    -0.09
    رده
    -0.09
     Dems
    -0.08
     Samar
    -0.08
     fac
    -0.08
     spur
    -0.08
    ulet
    -0.08
     sober
    -0.08
     Nou
    -0.08
    sy
    -0.08
     trav
    -0.08
    Positive Logits
    ONO
    0.13
    ekli
    0.11
    lier
    0.10
     Goldberg
    0.10
    libft
    0.10
     traffic
    0.10
    ocaly
    0.10
    wis
    0.10
    973
    0.10
     homo
    0.10
    665
    0.10
    �
    0.10
    isoft
    0.10
    姑
    0.10
    ozí
    0.09
    овер
    0.09
    aju
    0.09
     Kot
    0.09
    avl
    0.09
    omo
    0.09
    Activations Density 64.063%
    Loading dashboard...