© 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. 3848
    Prev
    Next
    INDEX
    Explanations

    Vice President or Vice Admiral

    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
    tod
    -0.08
    ç¨
    -0.08
    imas
    -0.08
    elling
    -0.07
    çı
    -0.07
    ider
    -0.07
    sip
    -0.07
     Scot
    -0.07
    /we
    -0.07
    vet
    -0.07
    POSITIVE LOGITS
     versa
    0.11
    MEA
    0.11
    yum
    0.10
    ssc
    0.09
    erts
    0.09
    arkan
    0.09
    .appspot
    0.09
    edu
    0.09
    imento
    0.09
    igel
    0.09
    Activations Density 0.156%

    No Known Activations