© 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. 4153
    Prev
    Next
    INDEX
    Explanations

    Tehran, form, tum, Ku, user, storage, country

    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
    /doc
    -0.11
    unj
    -0.10
     nav
    -0.10
     moc
    -0.10
    .sav
    -0.10
     Wich
    -0.10
    >manual
    -0.10
     Lik
    -0.10
    %n
    -0.09
     Conn
    -0.09
    POSITIVE LOGITS
    iol
    0.09
     comp
    0.08
    alf
    0.07
    dit
    0.07
    ior
    0.07
     internally
    0.07
     ditch
    0.07
    io
    0.07
     Chapman
    0.07
    oir
    0.07
    Activations Density 0.597%

    No Known Activations