© 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. 31513
    Prev
    Next
    INDEX
    Explanations

    names followed by verbs

    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
    æ³ķåŃIJ
    -0.08
    itten
    -0.07
    丹
    -0.07
    еди
    -0.07
    ç®
    -0.07
    èĢģ人家
    -0.06
    _proba
    -0.06
    erd
    -0.06
    çıĤ
    -0.06
    ishes
    -0.06
    POSITIVE LOGITS
     Gottes
    0.07
    è¯ķæİ¢
    0.07
    CION
    0.07
    ISTRA
    0.07
    >this
    0.07
    计ç®Ĺæľºè½¯ç¡¬ä»¶
    0.07
    portes
    0.07
    çļĦåĨħ
    0.06
    _timezone
    0.06
    {}
    0.06
    Activations Density 0.047%

    No Known Activations