© 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. 344
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    swick
    -0.10
     Budd
    -0.10
     Frid
    -0.10
     Harvey
    -0.09
    414
    -0.09
    �
    -0.09
    324
    -0.09
    UNS
    -0.09
     alph
    -0.09
    undai
    -0.09
    ylon
    -0.09
    석
    -0.09
     Oc
    -0.08
     nec
    -0.08
     Fior
    -0.08
    rosis
    -0.08
    制
    -0.08
     Reeves
    -0.08
    ote
    -0.08
    ries
    -0.08
    Positive Logits
    erras
    0.11
     zem
    0.11
    ingu
    0.11
    terr
    0.11
    Ｙ
    0.10
     mutual
    0.09
     Non
    0.09
     Dane
    0.09
    linger
    0.09
     Belt
    0.09
    .deb
    0.09
    ENTA
    0.09
     Sex
    0.09
     Id
    0.09
    zeigt
    0.09
     Obrázky
    0.09
    ertino
    0.09
     Eb
    0.09
    �
    0.09
     Tas
    0.09
    Activations Density 44.843%
    Loading dashboard...