© 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. 3758
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptors

    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
    amburger
    -0.09
     rewritten
    -0.08
    CM
    -0.08
    ennie
    -0.08
    vt
    -0.08
     Termin
    -0.07
     also
    -0.07
     lit
    -0.07
     Walker
    -0.07
     ALSO
    -0.07
    POSITIVE LOGITS
    aran
    0.09
     Nam
    0.09
     latter
    0.09
    sher
    0.09
    aroo
    0.08
     nam
    0.08
    /job
    0.08
    ATO
    0.08
    hil
    0.08
    .Photo
    0.08
    Activations Density 0.580%

    No Known Activations