© 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. 34375
    Prev
    Next
    INDEX
    Explanations

    conditionals and qualifications

    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
    åIJĮä¸Ģ个
    -0.08
    ì¶ķ
    -0.07
    æ¯ıä¸Ģ个ç»ĨèĬĤ
    -0.07
    缸åIJĮ
    -0.07
    uhan
    -0.07
    ä¸Ģè¿ŀ
    -0.07
    ä¸įåIJĮäºİ
    -0.07
    Metrics
    -0.07
    身æĹģçļĦ
    -0.07
    åĪ
    -0.07
    POSITIVE LOGITS
     never
    0.09
     range
    0.09
    never
    0.08
    ä¸įä¼ļåĩºçİ°
    0.08
     guarantee
    0.08
    ä¸ĬéĻIJ
    0.08
    iras
    0.08
    èĮĥåĽ´åĨħ使çĶ¨
    0.08
    èĮĥåĽ´åĨħçļĦ
    0.08
    _range
    0.08
    Activations Density 0.005%

    No Known Activations