© 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. 44
    Prev
    Next
    INDEX
    Explanations

    circuit board, arch development, search task

    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
    nero
    -0.10
    afa
    -0.09
     Genome
    -0.09
    _readable
    -0.09
     Gol
    -0.09
    Bins
    -0.09
    ört
    -0.09
    jsp
    -0.09
    requ
    -0.09
    WO
    -0.09
    POSITIVE LOGITS
    omics
    0.08
    ðŁĴ
    0.07
     bad
    0.07
     Orchard
    0.07
    ص
    0.07
    ayers
    0.07
     Synd
    0.07
     Sm
    0.07
    .runner
    0.07
     yr
    0.07
    Activations Density 3.163%

    No Known Activations