© 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. 14366
    Prev
    Next
    INDEX
    Explanations

    organic acid

    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
    æŃ¤ä¸¾
    -0.07
    å¦Ĥå®ŀ
    -0.06
    æĿIJ
    -0.06
    ä¸įä¸ĭ
    -0.06
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.06
     bol
    -0.06
     Rounds
    -0.06
    æİĴåįµæľŁ
    -0.06
    èģĶéĺ²èģĶæݧ
    -0.06
     Arm
    -0.05
    POSITIVE LOGITS
    oley
    0.07
    ifice
    0.07
    Ñģнов
    0.07
    tores
    0.07
    morgan
    0.07
    ç»ĵå°¾
    0.07
    ãĤĦãģĹ
    0.07
    åħ´åįİ
    0.07
    flix
    0.07
    indow
    0.07
    Activations Density 0.020%

    No Known Activations