© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22301
    Prev
    Next
    INDEX
    Explanations

    prospective cohort incident outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    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
    ovable
    -0.09
    å®ŀéªĮ
    -0.07
    éłĵ
    -0.07
    湿çĸ£
    -0.06
    èİħ
    -0.06
    çļĦå®ŀéªĮ
    -0.06
    .constructor
    -0.06
    å®ŀéªĮæķĻåѦ
    -0.06
    çļĦ人工
    -0.06
     experiment
    -0.06
    POSITIVE LOGITS
     predictors
    0.11
     nhan
    0.10
     cohorts
    0.09
     cohort
    0.09
     frail
    0.09
    istre
    0.08
    jectories
    0.08
     epidemi
    0.08
    è°
    0.08
     baseline
    0.08
    Activations Density 1.152%

    No Known Activations