© 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. 62156
    Prev
    Next
    INDEX
    Explanations

    rates of Muslim couples

    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
    gh
    -0.07
    æľīåIJį
    -0.07
    ergen
    -0.06
    移è¡Į
    -0.06
    rowse
    -0.06
    对人
    -0.06
    å±±ä¹ĭ
    -0.06
    éģ¥
    -0.06
    Ñģл
    -0.06
    ockey
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºåħ¶
    0.08
    æīĵåĸ·åļı
    0.08
    è¿Ŀåıįä¸Ĭè¿°
    0.08
     뾨
    0.07
    emed
    0.07
    æľ¨æĸ¯
    0.07
    aar
    0.07
    ä»»ä½ķå½¢å¼ıçļĦ
    0.07
    EXPECTED
    0.07
    åĽłä¸ºä»ĸ
    0.07
    Activations Density 0.199%

    No Known Activations