© 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. 469
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    IFn
    -0.11
    eni
    -0.10
    aml
    -0.10
     kolo
    -0.10
    Ｖ
    -0.10
    incy
    -0.09
    ニニ
    -0.09
    istrovství
    -0.09
     Wein
    -0.09
     Juice
    -0.09
    699
    -0.09
     Kro
    -0.08
    �
    -0.08
    ickers
    -0.08
    orde
    -0.08
     toxin
    -0.08
    Periph
    -0.08
    engin
    -0.08
    sy
    -0.08
    laden
    -0.08
    Positive Logits
    VC
    0.11
     VC
    0.10
     Vul
    0.09
     Jas
    0.09
    APPER
    0.09
    igits
    0.08
     Barr
    0.08
    485
    0.08
     Jame
    0.08
    折
    0.08
    jas
    0.08
     centuries
    0.08
    igu
    0.08
    ello
    0.08
     barracks
    0.08
     Serge
    0.08
    COMMON
    0.08
    oins
    0.08
     suff
    0.08
     barr
    0.08
    Activations Density 46.023%
    Loading dashboard...