© 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. 49879
    Prev
    Next
    INDEX
    Explanations

    -west followed by airport

    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
    æĿ¥çĶµåĴ¨è¯¢
    -0.08
     Zweck
    -0.07
    bereit
    -0.07
    leti
    -0.07
    讨
    -0.06
    ä¸ĵ家表示
    -0.06
    èĥ½çĶ¨
    -0.06
     виÑģ
    -0.06
    åı¯ä»¥çĶ¨
    -0.06
    æ·¡æ·¡
    -0.06
    POSITIVE LOGITS
    iente
    0.09
    æĬĬä¸Ģ个
    0.08
    æĢĿæĺİ
    0.08
    å°ıé¾Ļ
    0.08
    å°Ĩä¸Ģ个
    0.07
     followed
    0.07
    acca
    0.07
    avier
    0.07
     gevol
    0.07
    åĴĮæ³ķå¾ĭ
    0.07
    Activations Density 0.013%

    No Known Activations