© 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. 45706
    Prev
    Next
    INDEX
    Explanations

    model or system

    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
    iae
    -0.07
    ç´«
    -0.06
     nonzero
    -0.06
    /generated
    -0.06
    uzzi
    -0.06
    å¹´å¹´
    -0.06
    z
    -0.06
    æķ°éĩıåĴĮ
    -0.06
    abilia
    -0.06
    çĶ¨ä½ľ
    -0.06
    POSITIVE LOGITS
    管çIJĨ模å¼ı
    0.13
    模å¼ı
    0.12
    模å¼ıä¸Ń
    0.11
    模å¼ıçļĦ
    0.11
    åıijå±ķ模å¼ı
    0.11
    à¹ģà¸ļà¸ļ
    0.10
    çIJĨ念
    0.10
    æĸ°æ¨¡å¼ı
    0.10
    è¿IJèIJ¥æ¨¡å¼ı
    0.10
     reliance
    0.10
    Activations Density 0.335%

    No Known Activations