© 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. 508
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     err
    -0.12
    �能
    -0.12
     Err
    -0.11
     er
    -0.11
     vic
    -0.11
     Reid
    -0.10
    sek
    -0.10
    .er
    -0.10
    �
    -0.10
     ear
    -0.10
    indr
    -0.10
    ousing
    -0.10
    rieg
    -0.10
    aldi
    -0.10
    가는
    -0.10
    senal
    -0.10
     twitch
    -0.10
    egra
    -0.10
    longleftrightarrow
    -0.09
     Lair
    -0.09
    Positive Logits
    fy
    0.11
     DP
    0.10
    agu
    0.09
    歡
    0.09
    ers
    0.09
     đâu
    0.09
     addTarget
    0.09
     dp
    0.09
    ment
    0.08
     resp
    0.08
    out
    0.08
    ians
    0.08
    uy
    0.08
    月
    0.08
     Kyle
    0.08
     Amen
    0.08
     prop
    0.08
     Font
    0.08
     abbreviated
    0.08
    ertas
    0.08
    Activations Density 45.271%
    Loading dashboard...