© 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. 8435
    Prev
    Next
    INDEX
    Explanations

    Availability, template, get, graph, node, Field

    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
    ->
    -0.09
    ::
    -0.09
    ly
    -0.09
    fully
    -0.08
    ually
    -0.08
    manship
    -0.08
    or
    -0.08
    ecal
    -0.08
    -↵
    -0.07
    bv
    -0.07
    POSITIVE LOGITS
    hari
    0.10
    alth
    0.10
    uits
    0.10
    ities
    0.09
    plr
    0.09
    kad
    0.09
    npos
    0.09
    chez
    0.09
     Erot
    0.09
    heim
    0.09
    Activations Density 0.019%

    No Known Activations