© 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. 21584
    Prev
    Next
    INDEX
    Explanations

    constructor parameters

    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
    sten
    -0.08
    ÑĤивов
    -0.07
    æĬĵå®ŀ
    -0.07
    å°±çĽ¸å½ĵäºİ
    -0.07
    èIJ½ä¸ĭ
    -0.07
    veja
    -0.07
    /root
    -0.07
    rita
    -0.06
    eux
    -0.06
    createElement
    -0.06
    POSITIVE LOGITS
    æ¯Ĵ
    0.07
    asal
    0.07
    个æĸ¹éĿ¢
    0.07
    对ä¸Ĭè¿°
    0.07
    asio
    0.07
     Neub
    0.07
    ä¸įå¿į
    0.07
    asso
    0.07
    对æĪijåĽ½
    0.07
    å¯¹æľªæĿ¥
    0.06
    Activations Density 0.120%

    No Known Activations