© 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. 501
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
    ForObject
    -0.12
     Ari
    -0.10
    ocal
    -0.10
     search
    -0.10
     hor
    -0.09
    �
    -0.09
     "?"
    -0.09
     Hast
    -0.09
     Pry
    -0.09
    แหล
    -0.09
    eto
    -0.09
     Ends
    -0.09
    -&
    -0.09
    aus
    -0.09
     sour
    -0.09
    pling
    -0.09
    513
    -0.09
    _ptrs
    -0.09
    อบ
    -0.09
    uji
    -0.09
    Positive Logits
     Planner
    0.11
    (inner
    0.10
    ouch
    0.10
     Budd
    0.10
    かわ
    0.10
     inner
    0.10
    _UC
    0.10
    172
    0.10
     Vincent
    0.10
     Inner
    0.09
    vin
    0.09
     Tao
    0.09
     Tavern
    0.09
    151
    0.09
    inner
    0.09
    ieri
    0.09
    sson
    0.09
     P
    0.09
    漂
    0.09
    van
    0.09
    Activations Density 52.264%
    Loading dashboard...