© 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. 38854
    Prev
    Next
    INDEX
    Explanations

    directly followed by impact or relation

    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
    (Editor
    -0.08
     entirety
    -0.08
     gradually
    -0.08
     надлежа
    -0.08
     altogether
    -0.08
    æĽ´å®īåħ¨
    -0.08
    ิà¸ķิ
    -0.07
     sometime
    -0.07
    åį³ä½¿æĺ¯
    -0.07
    æĢ»ä½ĵè¦ģæ±Ĥ
    -0.07
    POSITIVE LOGITS
    缴æݥ影åĵį
    0.08
    èĪ
    0.08
    缴æݥ影åĵįåĪ°
    0.07
    缴æİ¥åħ³ç³»åĪ°
    0.07
    åı¯ä»¥çĽ´æİ¥
    0.07
    ë°Ķë¡ľ
    0.07
    åħ³ç³»åĪ°
    0.07
    åĴĮæľĢ
    0.07
     directly
    0.07
    ä½ĵçİ°åľ¨
    0.07
    Activations Density 0.026%

    No Known Activations