© 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. 26002
    Prev
    Next
    INDEX
    Explanations

    derivatives of 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
    æ¬ł
    -0.08
    ç»ıä¿¡
    -0.07
    agnost
    -0.07
    icits
    -0.07
    ukah
    -0.07
     Marks
    -0.07
    æĹ©é¤IJåIJİ
    -0.07
    è¿ĶåĽŀåĪĹ表
    -0.07
    Tester
    -0.06
    خر
    -0.06
    POSITIVE LOGITS
     Rewrite
    0.07
     rewrite
    0.07
    æĸ¹ä¾¿
    0.07
    åĴĮ西
    0.07
    为äºĨæĸ¹ä¾¿
    0.07
     expressions
    0.07
    ummer
    0.07
    vil
    0.07
     Paradise
    0.07
    æĽ´æĸ¹ä¾¿
    0.07
    Activations Density 0.004%

    No Known Activations