© 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. 326
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     Rim
    -0.11
    atile
    -0.10
    रण
    -0.10
    incer
    -0.10
    mdb
    -0.09
     Millennium
    -0.09
    ignon
    -0.09
     ambit
    -0.09
    akah
    -0.09
     Personnel
    -0.09
    ble
    -0.09
     Dick
    -0.09
     recycled
    -0.09
     Steph
    -0.09
    hip
    -0.09
     drip
    -0.09
     Coff
    -0.09
    -navigation
    -0.09
    ingle
    -0.09
    259
    -0.09
    Positive Logits
    reo
    0.11
     wand
    0.11
    apy
    0.11
     Maison
    0.10
    nces
    0.10
    ∨
    0.10
    Rnd
    0.10
    wand
    0.10
    nod
    0.10
     Wand
    0.10
     defe
    0.10
     Sears
    0.10
    ienda
    0.09
     Nag
    0.09
     Wan
    0.09
    ýt
    0.09
    729
    0.09
    totalCount
    0.09
     ◄
    0.09
     Fountain
    0.09
    Activations Density 51.434%
    Loading dashboard...