© 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. 29735
    Prev
    Next
    INDEX
    Explanations

    method or approach

    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
    åij½çļĦ
    -0.07
    umat
    -0.07
    è°ĥæŁ¥ç»ĵæŀľ
    -0.07
    æĥ³å¾Ĺ
    -0.07
    åħ³èģĶæĢ§
    -0.06
    athon
    -0.06
    uncan
    -0.06
    æ¿®
    -0.06
    ä¸įèĥ½è¢«
    -0.06
    letin
    -0.06
    POSITIVE LOGITS
     method
    0.13
    æĸ¹æ³ķè¿Ľè¡Į
    0.12
    æ³ķåĴĮ
    0.12
    æ³ķ
    0.12
    æĸ¹æ³ķ
    0.12
    æ³ķæĺ¯
    0.12
    æ³ķçŃī
    0.11
    æĸ¹æ³ķæĿ¥
    0.11
    è¿Ļç§įæĸ¹æ³ķ
    0.11
     approach
    0.11
    Activations Density 0.204%

    No Known Activations