© 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. 11732
    Prev
    Next
    INDEX
    Explanations

    waterproof properties

    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
    Scr
    -0.07
    群ä½ĵ
    -0.07
    ianti
    -0.07
    éģ¨æ¸¸
    -0.07
    enberg
    -0.07
    olare
    -0.07
    gaz
    -0.07
    WithValue
    -0.07
     Scrap
    -0.07
    oth
    -0.07
    POSITIVE LOGITS
     waterproof
    0.14
    湿
    0.14
     moisture
    0.13
     Waterproof
    0.13
    éĺ²æ½®
    0.12
    éĺ²æ°´
    0.12
    潮湿
    0.12
    æ¿ķ
    0.12
     wet
    0.12
    湿æ°Ķ
    0.12
    Activations Density 0.075%

    No Known Activations