© 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. 2487
    Prev
    Next
    INDEX
    Explanations

    numbers followed by punctuation

    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
     kepad
    -0.08
    ou
    -0.07
    ardon
    -0.07
    ä¸įæĥĬ
    -0.06
    æĸ¹åľĨ
    -0.06
    æĹłéĹ»
    -0.06
    ikov
    -0.06
    个åŃIJ
    -0.06
    scious
    -0.06
    彩äºij
    -0.06
    POSITIVE LOGITS
    <Input
    0.07
    йда
    0.07
     пÑĢопи
    0.07
    _flags
    0.07
     pales
    0.07
    ibri
    0.07
    人家
    0.06
    è¼ĶåĬ©
    0.06
    icur
    0.06
    ارÙĩ
    0.06
    Activations Density 0.014%

    No Known Activations