© 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. 30031
    Prev
    Next
    INDEX
    Explanations

    thanks and personal actions

    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
    çݺ
    -0.07
    èĢĮä½ľä¸º
    -0.07
    ldb
    -0.07
    é¡¿äºĨ
    -0.07
    usters
    -0.07
    èIJ§
    -0.07
    æ°¸è¿ľæĺ¯
    -0.07
    ä½łåı¯èĥ½ä¼ļ
    -0.07
    èĪįåĪ©
    -0.07
    éķ¿å¹´
    -0.07
    POSITIVE LOGITS
    æĪijè¿ĺæĺ¯
    0.08
    å®
    0.07
    thanks
    0.07
     thanks
    0.07
    ä»Ĭ度ãģ¯
    0.07
     Thanks
    0.07
    æĦŁè°¢æĤ¨çļĦ
    0.07
     thank
    0.07
     hov
    0.06
     বà§ģ
    0.06
    Activations Density 0.535%

    No Known Activations