© 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. 9901
    Prev
    Next
    INDEX
    Explanations

    A-negative blood type

    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
    èĦ¸åŀĭ
    -0.07
    ax
    -0.07
    ao
    -0.06
    èĻ½å°ı
    -0.06
    abo
    -0.06
    iru
    -0.06
    c
    -0.06
    chip
    -0.06
     trub
    -0.06
    icu
    -0.06
    POSITIVE LOGITS
    µ
    0.08
    Tes
    0.07
    åĴĮçĻ½
    0.07
    สà¸Ļิà¸Ĺ
    0.07
    Clr
    0.07
    çļĵ
    0.07
    Ŀ
    0.07
    Lifetime
    0.07
    åĴĮåİ¿
    0.07
    elsius
    0.07
    Activations Density 0.002%

    No Known Activations