© 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. 3733
    Prev
    Next
    INDEX
    Explanations

    code delimiters and structure

    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
    chie
    -0.10
    cod
    -0.09
    æĺ
    -0.09
    eman
    -0.09
    ees
    -0.09
    aran
    -0.09
    azon
    -0.09
    aring
    -0.09
     essentially
    -0.09
    nan
    -0.09
    POSITIVE LOGITS
    iana
    0.09
    .lu
    0.08
    owl
    0.08
    >čč↵
    0.08
    bild
    0.08
     cre
    0.08
    .icons
    0.07
    unn
    0.07
    ÑĤоÑĢ
    0.07
     suite
    0.07
    Activations Density 0.184%

    No Known Activations