© 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. 3815
    Prev
    Next
    INDEX
    Explanations

    name Birth date – Death date

    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
    ocker
    -0.09
    ua
    -0.09
    hear
    -0.07
     Mej
    -0.07
    ark
    -0.07
    chor
    -0.07
    nan
    -0.07
     palm
    -0.07
    erner
    -0.07
    chlor
    -0.07
    POSITIVE LOGITS
    idis
    0.10
    mps
    0.09
    umba
    0.09
    иÑģÑĤ
    0.09
    atts
    0.09
     marshal
    0.09
     Serg
    0.09
    onna
    0.09
    ave
    0.09
    ist
    0.09
    Activations Density 0.095%

    No Known Activations