© 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. 330
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    oret
    -0.12
     Far
    -0.12
    obus
    -0.12
    990
    -0.11
    PIO
    -0.11
    /operators
    -0.09
    ıy
    -0.09
     nas
    -0.09
     FAR
    -0.09
    �
    -0.09
    fst
    -0.09
    bul
    -0.09
    oğ
    -0.09
    ayd
    -0.09
     bulbs
    -0.09
     hug
    -0.08
     Tommy
    -0.08
     bulb
    -0.08
     Cunningham
    -0.08
    els
    -0.08
    Positive Logits
     Roose
    0.10
    loor
    0.10
    ialis
    0.10
    nothrow
    0.09
    抵
    0.09
    ullo
    0.09
    ALTH
    0.09
    lâm
    0.09
    念
    0.09
     Sims
    0.09
    BJECT
    0.09
     Blink
    0.09
    Ģ
    0.09
    Edges
    0.09
    alth
    0.09
    emand
    0.09
     Naked
    0.09
     ₹
    0.09
    ccione
    0.09
    icken
    0.09
    Activations Density 49.103%
    Loading dashboard...