© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 241
    Prev
    Next
    INDEX
    Explanations

    medical abbreviations and parenthesized disambiguation

    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
    uese
    -0.09
    ýt
    -0.08
    SingleOrDefault
    -0.08
     meaningful
    -0.08
    sons
    -0.08
    night
    -0.08
    rang
    -0.07
    oger
    -0.07
    rend
    -0.07
    å½ķ
    -0.07
    POSITIVE LOGITS
    ICLE
    0.09
     typ
    0.08
     skirts
    0.08
    cht
    0.07
    ffect
    0.07
    ';↵↵↵↵
    0.07
    grund
    0.07
     Pruitt
    0.07
    '↵↵↵↵
    0.07
    itect
    0.07
    Activations Density 3.755%

    No Known Activations