© 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. 55389
    Prev
    Next
    INDEX
    Explanations

    code structure usage

    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
     companion
    -0.08
    acr
    -0.07
    eng
    -0.07
     unless
    -0.07
     Mun
    -0.07
     Hir
    -0.07
     cop
    -0.07
     Jain
    -0.07
     Companion
    -0.07
     companions
    -0.06
    POSITIVE LOGITS
    /***************************************************************************↵
    0.10
    ipo
    0.10
    kek
    0.10
    oti
    0.10
     scr
    0.10
    ndl
    0.09
    ppo
    0.09
    =__
    0.09
    yh
    0.09
    borg
    0.09
    Activations Density 0.008%

    No Known Activations