© 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. 11682
    Prev
    Next
    INDEX
    Explanations

    population numbers, amounts, or ratios

    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
    èĭ¥å¹²ä¸ª
    -0.07
    èį£åįİ
    -0.06
     “
    -0.06
    ç¿°
    -0.06
    缮ä¸Ń
    -0.06
    å¼Ĥ
    -0.06
    大å¼Ģ
    -0.06
     weigh
    -0.06
    æīĭ足
    -0.06
    æ¸
    -0.06
    POSITIVE LOGITS
    åįłæ¯Ķ
    0.11
    æ¯Ķä¾ĭ为
    0.10
    Ratio
    0.10
    æ¯Ķçİĩ
    0.10
    _ratio
    0.10
    irs
    0.10
     ratio
    0.10
     Ratio
    0.10
    ratio
    0.09
     ratios
    0.09
    Activations Density 0.167%

    No Known Activations