© 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. 437
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    unya
    -0.10
    osg
    -0.10
    BeforeEach
    -0.10
    cy
    -0.10
    .FontStyle
    -0.10
    cano
    -0.10
    oram
    -0.09
    ideographic
    -0.09
     OnTriggerEnter
    -0.09
    stown
    -0.09
     equipments
    -0.09
     Franken
    -0.09
     repl
    -0.09
    arkin
    -0.09
    切
    -0.09
    axon
    -0.09
    DeltaTime
    -0.09
     Gaw
    -0.09
    　　　 　 　 　
    -0.09
    _epsilon
    -0.09
    Positive Logits
     proof
    0.11
     Proof
    0.10
     Furn
    0.10
    -proof
    0.09
     �
    0.09
    577
    0.09
     MP
    0.09
     mirrored
    0.09
     Bomb
    0.09
     Vac
    0.09
     exec
    0.08
     stale
    0.08
     Window
    0.08
     AM
    0.08
    .:.:.:
    0.08
     meth
    0.08
     Far
    0.08
     hatch
    0.08
     remot
    0.08
    ular
    0.08
    Activations Density 49.552%
    Loading dashboard...