© 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. 42843
    Prev
    Next
    INDEX
    Explanations

    continually, constantly, developing

    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
    ä¸Ģ缴ä¿ĿæĮģ
    -0.08
    handling
    -0.07
    éĥ¨åĪĨåĨħ容
    -0.07
    æŃ£å¼ıå¼Ģå§ĭ
    -0.07
    å®Įåħ¨æ²¡æľī
    -0.07
    leo
    -0.07
    æī±ãģĦ
    -0.07
    łí
    -0.07
    ä¸įåģļ
    -0.07
    inqui
    -0.07
    POSITIVE LOGITS
     sayıda
    0.09
    ç¶ļãģı
    0.08
    ä¸įåģľçļĦ
    0.08
    ä¸įæģ¯
    0.08
    ä¸įæĸŃåľ°
    0.08
    ä¸įæĸŃçļĦ
    0.08
    ä¸įä¼ij
    0.08
    кÑĢаÑĤно
    0.08
    emente
    0.08
    sic
    0.08
    Activations Density 0.044%

    No Known Activations