© 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. 57377
    Prev
    Next
    INDEX
    Explanations

    .hpp include statements

    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
    )["
    -0.11
     csr
    -0.11
    /Private
    -0.11
    {text
    -0.10
    erview
    -0.10
    lec
    -0.10
    ervo
    -0.10
    ession
    -0.10
    mez
    -0.10
    oes
    -0.09
    POSITIVE LOGITS
    ala
    0.07
     Victor
    0.07
     Coll
    0.07
     brand
    0.06
     dés
    0.06
    ako
    0.06
     Sik
    0.06
    iku
    0.06
    inals
    0.06
     deferred
    0.06
    Activations Density 0.016%

    No Known Activations