© 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. 54507
    Prev
    Next
    INDEX
    Explanations

    Summary Calendar

    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
    oles
    -0.10
    AME
    -0.09
    ier
    -0.08
     anyways
    -0.08
     vs
    -0.08
    egal
    -0.08
    ieve
    -0.07
     referred
    -0.07
     initiated
    -0.07
    ichte
    -0.07
    POSITIVE LOGITS
    .bootstrap
    0.10
    ombat
    0.10
    phan
    0.09
     lab
    0.09
    /pub
    0.09
    fee
    0.09
    azi
    0.09
    /lab
    0.08
    ascript
    0.08
    vos
    0.08
    Activations Density 0.006%

    No Known Activations