© 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. 4258
    Prev
    Next
    INDEX
    Explanations

    acquired immunodeficiency virus

    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
    ceb
    -0.09
    anch
    -0.09
     Hath
    -0.08
     bac
    -0.08
     Classics
    -0.08
     Bender
    -0.08
    yahoo
    -0.08
     hosp
    -0.08
    dice
    -0.08
    ounty
    -0.08
    POSITIVE LOGITS
     Greatest
    0.08
    .TestTools
    0.08
     pedest
    0.08
     Vere
    0.08
    iod
    0.08
    vere
    0.07
    íĻĶ
    0.07
    brig
    0.07
     Colt
    0.07
    ged
    0.07
    Activations Density 0.948%

    No Known Activations