© 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. 371
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    iger
    -0.12
    iny
    -0.10
     Fey
    -0.10
    〕
    -0.10
    igers
    -0.10
    iner
    -0.09
     Dion
    -0.09
    HW
    -0.09
     Cunningham
    -0.09
    inity
    -0.09
    _paragraph
    -0.09
    lesi
    -0.09
    wt
    -0.09
    ework
    -0.09
     Tou
    -0.08
    二二
    -0.08
     освещ
    -0.08
     cyan
    -0.08
    _strike
    -0.08
     Pill
    -0.08
    Positive Logits
    unge
    0.10
     according
    0.10
     Cot
    0.10
     MSR
    0.09
    aret
    0.09
     addCriterion
    0.09
    oire
    0.09
     Pence
    0.09
    IDGET
    0.09
    /inet
    0.09
    據
    0.09
    aired
    0.09
    outu
    0.09
    ğmen
    0.09
    aus
    0.09
     Nit
    0.09
    920
    0.09
    �
    0.09
     Crimes
    0.09
    iples
    0.09
    Activations Density 50.229%
    Loading dashboard...