© 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. 463
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     mainland
    -0.11
     equ
    -0.10
    arta
    -0.10
    662
    -0.09
     suce
    -0.09
     seg
    -0.09
     finishes
    -0.09
    erman
    -0.09
     toy
    -0.09
    ží
    -0.09
    Mocks
    -0.09
    ward
    -0.09
    Aura
    -0.09
    enda
    -0.09
     arm
    -0.09
    /MIT
    -0.09
     bif
    -0.09
     TV
    -0.08
    晴
    -0.08
    ych
    -0.08
    Positive Logits
     epis
    0.10
    evi
    0.10
     McCoy
    0.10
     consensus
    0.09
     pii
    0.09
     piping
    0.09
    müş
    0.09
    ATIONAL
    0.09
    akt
    0.09
    avings
    0.09
     Force
    0.09
    iping
    0.09
     playground
    0.09
    [text
    0.09
    HLT
    0.09
     Ende
    0.09
    цит
    0.08
     pipes
    0.08
    /archive
    0.08
    班
    0.08
    Activations Density 46.439%
    Loading dashboard...