© 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. 55573
    Prev
    Next
    INDEX
    Explanations

    self

    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
    PTS
    -0.10
     probable
    -0.10
    bib
    -0.10
    ovie
    -0.10
    PS
    -0.09
    CTS
    -0.09
     Tags
    -0.09
    alm
    -0.09
    /tag
    -0.09
     Refresh
    -0.09
    POSITIVE LOGITS
     puss
    0.09
     internally
    0.08
     lear
    0.08
     Neh
    0.07
    endi
    0.07
    éķ
    0.07
     faculties
    0.07
     learns
    0.07
    uild
    0.07
     Borrow
    0.07
    Activations Density 0.003%

    No Known Activations