© 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. 57121
    Prev
    Next
    INDEX
    Explanations

    integrates, actively, compatible, abundant

    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
    onden
    -0.08
    æŁIJç§įç¨ĭ度ä¸Ĭ
    -0.08
    æŁIJ个
    -0.08
    æŁIJ人
    -0.07
     Edited
    -0.07
    aped
    -0.07
    андÑĢ
    -0.07
    alti
    -0.07
    arked
    -0.07
    дÑĢеÑģ
    -0.07
    POSITIVE LOGITS
    并积æŀģ
    0.10
    并åĪ©çĶ¨
    0.09
    并åıĬæŶ
    0.08
    并
    0.08
    åĴĮå®ĮåĸĦ
    0.07
    !
    0.07
    ç§ijåѦçļĦ
    0.07
    åĴĮåĪĽæĸ°
    0.07
    åľ°è¿Ľè¡Į
    0.07
     versatile
    0.07
    Activations Density 0.004%

    No Known Activations