© 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. 505
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    �
    -0.12
     pisc
    -0.11
     tandem
    -0.10
    .netbeans
    -0.10
     Dalton
    -0.10
    　　　　　 　
    -0.10
     LIABILITY
    -0.10
    :::::
    -0.10
     Pou
    -0.10
    uxt
    -0.10
    isse
    -0.10
    _alias
    -0.10
     facult
    -0.10
    thur
    -0.10
    �
    -0.09
    alon
    -0.09
    .Ui
    -0.09
    linky
    -0.09
    itol
    -0.09
    553
    -0.09
    Positive Logits
     nationalism
    0.11
     Fr
    0.10
     tang
    0.10
    elder
    0.10
     McGill
    0.10
    -fr
    0.09
     firsthand
    0.09
     block
    0.09
     lane
    0.09
    eld
    0.09
     coun
    0.09
     cq
    0.09
     memor
    0.09
     Tri
    0.09
     Div
    0.09
    "@
    0.09
    chl
    0.09
     early
    0.09
     Coun
    0.08
     hood
    0.08
    Activations Density 56.361%
    Loading dashboard...