© 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. 45076
    Prev
    Next
    INDEX
    Explanations

    patients and subjects experiencing conditions

    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
    为人们
    -0.09
    orte
    -0.09
    触è§Ĵ
    -0.08
    ris
    -0.08
    ört
    -0.07
    รà¸ĩà¹ģ
    -0.07
    æĪijä¸Ģ个人
    -0.07
     Babies
    -0.07
    ä¼ļ让人
    -0.07
    è´¨çļĦ
    -0.07
    POSITIVE LOGITS
     who
    0.10
    ìĹIJê²Į
    0.08
     experiencing
    0.08
     whom
    0.07
     whose
    0.07
     recovering
    0.07
    ä½ĵåĨħçļĦ
    0.07
     aged
    0.07
    ç»ıåİĨçļĦ
    0.07
     habitual
    0.07
    Activations Density 0.475%

    No Known Activations