© 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. 56406
    Prev
    Next
    INDEX
    Explanations

    receptor, synthase, oxide, syndrome, centres

    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
     *[
    -0.10
     ([
    -0.10
    eye
    -0.09
     [
    -0.09
    nore
    -0.08
    /activity
    -0.08
    etto
    -0.08
     ãĢIJ
    -0.08
    fire
    -0.08
     deserved
    -0.08
    POSITIVE LOGITS
    .${
    0.09
    _By
    0.09
     emit
    0.09
    #${
    0.09
    chner
    0.09
    ABCDEFGHI
    0.08
     names
    0.08
     poo
    0.08
     pi
    0.08
    hal
    0.08
    Activations Density 0.076%

    No Known Activations