© 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. 488
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Fulton
    -0.10
    302
    -0.10
     Se
    -0.09
     comple
    -0.09
    式
    -0.09
     Lamb
    -0.09
     centrif
    -0.09
     Woj
    -0.09
    apan
    -0.09
     Zion
    -0.09
    887
    -0.09
    umbo
    -0.08
     blind
    -0.08
    yles
    -0.08
    urity
    -0.08
    492
    -0.08
    shm
    -0.08
    asse
    -0.08
     purity
    -0.08
     Megan
    -0.08
    Positive Logits
     Hin
    0.12
     Kramer
    0.11
    uguay
    0.11
    elden
    0.11
    jeme
    0.10
    minus
    0.10
    alara
    0.10
     minus
    0.10
    wend
    0.10
    elsing
    0.10
    enos
    0.10
    opic
    0.10
    ｛
    0.09
    uerdo
    0.09
    eldon
    0.09
    -Clause
    0.09
     ath
    0.09
    oupon
    0.09
    Bounding
    0.09
    ilyn
    0.09
    Activations Density 52.534%
    Loading dashboard...