© 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. 406
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     HIT
    -0.12
     viral
    -0.11
    acet
    -0.11
    bg
    -0.10
    resco
    -0.10
    ROTO
    -0.10
    antan
    -0.10
    监听页面
    -0.10
     Sul
    -0.10
     pand
    -0.10
    �
    -0.09
     Knox
    -0.09
     Kane
    -0.09
     Gon
    -0.09
    ment
    -0.09
    aket
    -0.09
    aten
    -0.09
    Expansion
    -0.09
    토토
    -0.09
    enter
    -0.09
    Positive Logits
    holm
    0.10
    idor
    0.10
    otor
    0.10
    雅
    0.10
     purge
    0.10
    卷
    0.09
    edia
    0.09
    ettel
    0.09
     Rudd
    0.09
     Legion
    0.09
     legitim
    0.09
     Tick
    0.09
    ymm
    0.09
     Sez
    0.09
    pole
    0.09
    nard
    0.09
    �
    0.09
    UILD
    0.09
    zia
    0.09
     Warwick
    0.09
    Activations Density 54.593%
    Loading dashboard...