© 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. 55948
    Prev
    Next
    INDEX
    Explanations

    ultrasound medical imaging

    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
    Unnamed
    -0.09
    erate
    -0.09
     Sem
    -0.09
    ìķ¼
    -0.09
    #=
    -0.09
    zag
    -0.08
    indr
    -0.08
    esch
    -0.08
    otope
    -0.08
    keiten
    -0.08
    POSITIVE LOGITS
    heet
    0.10
    gate
    0.09
    iaux
    0.08
     Gee
    0.08
     Fantastic
    0.07
    oge
    0.07
    driver
    0.07
    ifer
    0.07
    ument
    0.07
    ical
    0.07
    Activations Density 0.005%

    No Known Activations