© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 3390
    Prev
    Next
    INDEX
    Explanations

    pregnancy or pregnant

    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
    astic
    -0.10
    atur
    -0.09
    çľ
    -0.09
    .getChildren
    -0.08
    jeta
    -0.08
     incons
    -0.08
     Mast
    -0.08
     grilled
    -0.08
     Jenny
    -0.08
    anus
    -0.08
    POSITIVE LOGITS
    uez
    0.09
     trimest
    0.09
    nant
    0.08
     Women
    0.08
     ska
    0.08
     mare
    0.07
    STYPE
    0.07
    /application
    0.07
     pickle
    0.07
     hij
    0.07
    Activations Density 0.124%

    No Known Activations