© 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. 3193
    Prev
    Next
    INDEX
    Explanations

    identity, mental, caption, account, high, controller, comment, piano, string

    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
     Gle
    -0.09
    alten
    -0.09
    icos
    -0.09
    brain
    -0.09
    aut
    -0.09
    assa
    -0.08
     threaded
    -0.08
     Yad
    -0.08
    ugi
    -0.08
     External
    -0.08
    POSITIVE LOGITS
    IMS
    0.09
    urre
    0.09
     painters
    0.09
    gne
    0.09
    errated
    0.09
    pin
    0.09
    erial
    0.08
    oom
    0.08
    ordion
    0.08
    poi
    0.08
    Activations Density 0.668%

    No Known Activations