© 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. 425
    Prev
    Next
    Layer 20Layer 22
    INDEX
    Compare
    Explanations
    No Explanations Found
    Auto-Interp Tools
    Top Features by Cosine Similarity
    Embeds
    IFrame
    Link
    Negative Logits
     instead
    -0.13
    Pont
    -0.12
     totiž
    -0.11
     Instead
    -0.11
    RefCount
    -0.11
     вмест
    -0.10
     therefore
    -0.10
     dys
    -0.10
     thus
    -0.10
     Pont
    -0.10
    instead
    -0.10
    ço
    -0.10
    otti
    -0.10
     undocumented
    -0.10
    HITE
    -0.10
     Jab
    -0.10
     Shack
    -0.09
    Instead
    -0.09
    RLF
    -0.09
     Matches
    -0.09
    Positive Logits
    991
    0.13
     Cros
    0.10
     Oman
    0.10
     straw
    0.09
     Carm
    0.09
    801
    0.09
    -pad
    0.09
     Carmen
    0.09
     Tos
    0.09
     Tut
    0.09
    avn
    0.09
    霞
    0.09
    straint
    0.09
     ambush
    0.09
    ide
    0.09
    UT
    0.08
    halt
    0.08
    .getSeconds
    0.08
    빌
    0.08
     Leh
    0.08
    Activations Density 44.310%
    Loading dashboard...