© 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. 57539
    Prev
    Next
    INDEX
    Explanations

    deployment mode, running, playing

    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
    iced
    -0.09
    anca
    -0.08
     aff
    -0.08
     Reform
    -0.08
    intel
    -0.08
     bullet
    -0.07
    angu
    -0.07
     available
    -0.07
     cerebral
    -0.07
     tomorrow
    -0.07
    POSITIVE LOGITS
    EditMode
    0.10
    ullo
    0.10
    grading
    0.10
    otec
    0.09
     Horse
    0.09
    iffe
    0.09
     Sho
    0.09
    lx
    0.09
    itas
    0.09
     ward
    0.09
    Activations Density 0.069%

    No Known Activations