© 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. 390
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     sang
    -0.12
    080
    -0.11
     Sang
    -0.11
    asar
    -0.10
    �
    -0.10
     Suff
    -0.10
     Marcos
    -0.10
    alice
    -0.10
     decentral
    -0.10
     Hubb
    -0.10
    _notifier
    -0.10
    krom
    -0.10
    -git
    -0.10
    589
    -0.10
    iyon
    -0.10
    arges
    -0.10
     anarch
    -0.10
    ieri
    -0.10
     Leeds
    -0.10
    asury
    -0.09
    Positive Logits
     -
    0.13
     Universe
    0.11
     viet
    0.10
     young
    0.10
     Swan
    0.10
     Insider
    0.10
     cons
    0.10
     def
    0.09
    ---
    0.09
     --
    0.09
     Hank
    0.09
     >
    0.09
    ogan
    0.09
     PS
    0.09
     sever
    0.09
    wer
    0.09
    iah
    0.09
    ken
    0.09
     ---
    0.09
    op
    0.09
    Activations Density 58.699%
    Loading dashboard...