© 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. 22917
    Prev
    Next
    INDEX
    Explanations

    computational methods and procedures

    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
     oneself
    -0.08
     individ
    -0.07
    ä½łçļĦåIJįåŃĹ
    -0.07
     us
    -0.07
     themselves
    -0.07
    çĦ¶åIJİæĺ¯
    -0.06
    ying
    -0.06
    طب
    -0.06
     itself
    -0.06
    æĪij们就
    -0.06
    POSITIVE LOGITS
    åĴĮæĪijçļĦ
    0.08
    ãģĦãģĪ
    0.08
    ãģ¥ãģı
    0.08
    udeau
    0.08
     Mäd
    0.07
    ää
    0.07
    winkel
    0.07
    rou
    0.07
    ä¸Ĭæ·»
    0.07
     köt
    0.07
    Activations Density 0.099%

    No Known Activations