© 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. 57130
    Prev
    Next
    INDEX
    Explanations

    adhesive attachment

    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
    udeau
    -0.07
     zil
    -0.07
    даÑĤи
    -0.07
     tamp
    -0.07
     ÑĢазÑĢе
    -0.07
    æł¹æį®ä¸ªäºº
    -0.07
     ná»ģ
    -0.07
     Contrib
    -0.06
    hto
    -0.06
    eni
    -0.06
    POSITIVE LOGITS
     enabling
    0.09
    æĸ¹ä¾¿
    0.09
    以便
    0.09
    æĸ¹ä¾¿çļĦ
    0.09
    便äºİ
    0.08
     targeting
    0.08
     attachment
    0.08
    åı¯ä»¥åĴĮ
    0.08
     clashed
    0.08
     Enables
    0.08
    Activations Density 0.175%

    No Known Activations