© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Olmo-3-1025-7B
    5. 16-RES-MATRYOSHKA-65K
    7. 706
    Prev
    Next
    INDEX
    Explanations

    spontaneously occurring or generated

    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
    Reusable
    -0.10
    iosis
    -0.09
     Alive
    -0.09
    ioned
    -0.09
    urse
    -0.09
    /issues
    -0.09
     paraph
    -0.09
    uras
    -0.09
    irc
    -0.09
    -view
    -0.09
    POSITIVE LOGITS
    /auto
    0.13
    /manual
    0.13
     olarak
    0.11
    /by
    0.11
    -generated
    0.10
    /default
    0.10
    /internal
    0.10
     generated
    0.10
    /pre
    0.09
    aneous
    0.09
    Activations Density 1.768%

    No Known Activations