© 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. 8377
    Prev
    Next
    INDEX
    Explanations

    spio, spino, spont, spatio

    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
    per
    -0.09
     Ñģл
    -0.08
     republic
    -0.08
     spoiled
    -0.08
     Spoon
    -0.08
    asar
    -0.08
     Spiral
    -0.08
    edia
    -0.08
    enu
    -0.08
     spare
    -0.08
    POSITIVE LOGITS
    -License
    0.13
    iards
    0.11
     cord
    0.10
    unky
    0.10
    cosa
    0.10
    NING
    0.09
    cord
    0.09
    itta
    0.09
    ouflage
    0.09
    hower
    0.09
    Activations Density 0.286%

    No Known Activations