© 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. 447
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     bef
    -0.11
     punctuation
    -0.10
     Toll
    -0.10
    　イ
    -0.09
     Tent
    -0.09
    breadcrumbs
    -0.09
    าอย
    -0.09
    braco
    -0.09
    tent
    -0.09
     shr
    -0.09
     centered
    -0.09
    pref
    -0.09
    rib
    -0.09
    idente
    -0.09
    iphers
    -0.09
     Cow
    -0.09
     mul
    -0.09
     Burl
    -0.09
    gene
    -0.08
    igger
    -0.08
    Positive Logits
    �
    0.11
     Petite
    0.11
     opinion
    0.10
     �
    0.10
     Herald
    0.10
     consent
    0.09
    rets
    0.09
    翼
    0.09
     Kos
    0.09
     recomm
    0.09
    ulp
    0.09
    ubat
    0.09
    خو
    0.09
    :.:
    0.09
    tran
    0.09
    crest
    0.09
    功
    0.09
     Sas
    0.09
     DataView
    0.09
    らい
    0.09
    Activations Density 54.507%
    Loading dashboard...