© 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. 1175
    Prev
    Next
    INDEX
    Explanations

    human concepts and fundamental science

    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
    /extensions
    -0.09
     reported
    -0.09
    Bootstrap
    -0.09
     gratuita
    -0.09
    Uvs
    -0.09
     expérience
    -0.09
    .report
    -0.09
     cherry
    -0.09
    ottie
    -0.09
     retros
    -0.09
    POSITIVE LOGITS
    ankind
    0.11
     mankind
    0.11
     billions
    0.09
     fundamentally
    0.09
     fundamental
    0.09
     countless
    0.09
     human
    0.09
     millennia
    0.09
     parad
    0.09
     humans
    0.09
    Activations Density 5.130%

    No Known Activations