© 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. 4080
    Prev
    Next
    INDEX
    Explanations

    oxide particles

    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
     propagated
    -0.10
    lea
    -0.10
     expend
    -0.09
    ve
    -0.09
     harvesting
    -0.09
    atica
    -0.09
    ék
    -0.09
    Iss
    -0.09
    .Reader
    -0.09
     Soup
    -0.09
    POSITIVE LOGITS
    ijo
    0.09
    apat
    0.09
     pow
    0.09
     gran
    0.09
     Berger
    0.09
     crystall
    0.08
     deposited
    0.08
    ADE
    0.08
    gran
    0.08
     Pow
    0.08
    Activations Density 0.520%

    No Known Activations