© 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. 451
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     subt
    -0.13
     difficult
    -0.12
     difícil
    -0.11
    ees
    -0.10
     Bett
    -0.10
     easiest
    -0.10
    argo
    -0.10
     Carrier
    -0.10
    onym
    -0.10
     Campbell
    -0.10
    _finder
    -0.10
    easy
    -0.09
     Weg
    -0.09
     Memories
    -0.09
     zel
    -0.09
     easy
    -0.09
    oir
    -0.09
     difficile
    -0.09
     sometimes
    -0.09
    erty
    -0.09
    Positive Logits
    berman
    0.12
    τια
    0.10
     Rot
    0.10
    透
    0.10
     Uint
    0.10
    806
    0.10
    raman
    0.10
     UITableViewController
    0.09
    :Any
    0.09
    stk
    0.09
    inx
    0.09
     tol
    0.09
    ستی
    0.09
    bout
    0.09
    jh
    0.09
     Milton
    0.09
    etri
    0.09
     Recording
    0.09
     knex
    0.09
     Junk
    0.09
    Activations Density 42.946%
    Loading dashboard...