© 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. 30434
    Prev
    Next
    INDEX
    Explanations

    special characters and symbols

    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
    impa
    -0.07
    æľ¬ç«ĻåĨħ容
    -0.07
    éĶ¦æ¶Ľ
    -0.07
    æŶéĹ´åĴĮç²¾åĬĽ
    -0.07
    auga
    -0.07
    erty
    -0.07
    agian
    -0.07
    onav
    -0.07
    è¿Ŀæ³ķåĴĮä¸įèī¯ä¿¡æģ¯ä¸¾æĬ¥
    -0.07
    avax
    -0.07
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.08
    丹
    0.06
    æŁIJ个
    0.06
    bak
    0.06
    oons
    0.06
    æľ¬æ³ķ
    0.06
    æŁIJ
    0.06
    æŁIJåĢĭ
    0.06
     whatever
    0.06
    ÙįÙij
    0.06
    Activations Density 0.083%

    No Known Activations