© 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. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 4754
    Prev
    Next
    INDEX
    Explanations

    you after license agreement terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/olmo-3-saes/olmo-3-1025-7b
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lind
    -0.09
    hawks
    -0.08
     Clim
    -0.08
     Mild
    -0.08
    hev
    -0.08
     Blind
    -0.08
     neither
    -0.08
     Risk
    -0.08
     indirect
    -0.08
     elé
    -0.08
    POSITIVE LOGITS
     Cove
    0.09
    asmine
    0.09
    lene
    0.09
     Robbie
    0.08
     Ballet
    0.08
     Jesse
    0.08
    etr
    0.08
    upo
    0.08
    olor
    0.08
    /head
    0.08
    Activations Density 0.002%

    No Known Activations