© 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. 423
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Stub
    -0.11
     Franz
    -0.11
    antic
    -0.10
    ICT
    -0.10
     oversh
    -0.10
    ivia
    -0.10
    acier
    -0.10
     Wheat
    -0.10
    LIK
    -0.09
    �
    -0.09
    rike
    -0.09
     voks
    -0.09
     stat
    -0.09
    působ
    -0.09
     retros
    -0.09
     司
    -0.09
    �
    -0.09
    alendar
    -0.09
    -прав
    -0.09
    ades
    -0.09
    Positive Logits
     outr
    0.12
     Laguna
    0.12
    竞
    0.11
     lag
    0.11
     competition
    0.11
     Intelligence
    0.10
     sco
    0.10
    競
    0.10
     Cath
    0.10
     beat
    0.10
     Competition
    0.09
    ilies
    0.09
    oller
    0.09
     konk
    0.09
     hạng
    0.09
     رق
    0.09
     конкур
    0.09
    abeth
    0.09
     win
    0.09
     competitive
    0.09
    Activations Density 56.272%
    Loading dashboard...