© 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. 41136
    Prev
    Next
    INDEX
    Explanations

    usual or like

    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
    æį®è¯´
    -0.08
     presently
    -0.07
    å·®çĤ¹
    -0.07
    alled
    -0.07
    ética
    -0.07
    mites
    -0.07
     apparently
    -0.07
    lieder
    -0.07
    ISIBLE
    -0.07
    ecd
    -0.07
    POSITIVE LOGITS
    类似çļĦ
    0.10
    æѤ类
    0.10
     similar
    0.09
     подобнÑĭе
    0.09
    ä½ķåĨµ
    0.08
    åľ¨è¿Ļæł·çļĦ
    0.08
     подобнÑĭÑħ
    0.08
     подобного
    0.08
    ä¸ĢèĪ¬éĥ½ä¼ļ
    0.08
    æĽ´ä½ķåĨµ
    0.08
    Activations Density 0.205%

    No Known Activations