© 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. 54947
    Prev
    Next
    INDEX
    Explanations

    protein structure

    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
    ظ
    -0.09
    erland
    -0.09
    wap
    -0.09
    oland
    -0.08
    appl
    -0.08
     Karn
    -0.08
    abad
    -0.08
    æĴ
    -0.08
    Carthy
    -0.08
    ackbar
    -0.07
    POSITIVE LOGITS
    ]:↵↵↵
    0.09
    flate
    0.08
    dig
    0.08
    åı·
    0.08
    ());↵↵↵
    0.08
     Italians
    0.08
    hell
    0.08
     cet
    0.08
    irit
    0.08
     amore
    0.08
    Activations Density 0.168%

    No Known Activations