© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 26756
    Prev
    Next
    INDEX
    Explanations

    susceptibility to conditions or disease

    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
    åłĤçļĦ
    -0.07
     Thou
    -0.07
    æķĪæŀľ
    -0.07
    almente
    -0.07
    gal
    -0.06
    è¿ĩ硬
    -0.06
    /pol
    -0.06
    andel
    -0.06
    arel
    -0.06
    ະ
    -0.06
    POSITIVE LOGITS
    hood
    0.09
     vulnerability
    0.09
     Vulner
    0.09
    人群çļĦ
    0.08
    ability
    0.08
    æ»ĭäºĭ
    0.08
    ponent
    0.08
    ä¹ĭçªĹ
    0.08
    èĦĨå¼±
    0.08
     возникновениÑı
    0.08
    Activations Density 0.113%

    No Known Activations