© 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. 2845
    Prev
    Next
    INDEX
    Explanations

    of course

    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
    eu
    -0.10
     rec
    -0.09
    awe
    -0.09
    aved
    -0.08
     containment
    -0.08
    fone
    -0.08
    vertise
    -0.08
    eh
    -0.08
    mine
    -0.08
     sorts
    -0.08
    POSITIVE LOGITS
     course
    0.15
     COUR
    0.13
     Course
    0.12
    Course
    0.12
    /from
    0.11
    {↵↵↵
    0.10
    _course
    0.10
    course
    0.09
    -course
    0.09
    holm
    0.09
    Activations Density 0.118%

    No Known Activations