© 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. 64209
    Prev
    Next
    INDEX
    Explanations

    foreign characters and language

    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
    å·²ç»ıå°Ĩ
    -0.08
    éĹ®é¢ĺæŶ
    -0.08
    inerary
    -0.08
    æ¯Ķè¾ĥ严éĩį
    -0.07
    æ¯Ķè¾ĥéķ¿
    -0.07
    à¹Ģà¸ģีà¹Īยวà¸Ĥà¹īà¸Ńà¸ĩà¸ģัà¸ļ
    -0.07
    ôt
    -0.07
    utkan
    -0.07
    strup
    -0.07
    æĺ¯ä¸Ģ个éĿŀ常
    -0.07
    POSITIVE LOGITS
    éļıä¹ĭ
    0.13
    ä¹Łéļıä¹ĭ
    0.11
     accordingly
    0.10
    å¾Ĺ以
    0.09
    æį®æѤ
    0.08
     consequently
    0.08
     thereof
    0.08
     ÑģооÑĤвеÑĤÑģÑĤвенно
    0.08
    åıĸèĢĮ代ä¹ĭ
    0.08
    åľ¨åħ¶ä¸Ń
    0.08
    Activations Density 0.072%

    No Known Activations