© 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. 13550
    Prev
    Next
    INDEX
    Explanations

    you are, we offer

    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
    ritz
    -0.08
    æģĴå¿ĥ
    -0.07
    纲è¦ģ
    -0.07
    ahr
    -0.07
    waan
    -0.07
    दान
    -0.07
    awan
    -0.07
    åħ¢
    -0.07
    ¥
    -0.07
    ä¸ĢåIJĮ
    -0.07
    POSITIVE LOGITS
     Ned
    0.07
    åı¤å±ĭ
    0.06
    è¿Ļç§įä¸ľè¥¿
    0.06
     ÙĪاس
    0.06
     Ov
    0.06
    Ø¢Ùħد
    0.06
    land
    0.06
    åĴĮä¸ĭ
    0.06
    æľ¬é¢ĺçŃĶæ¡Ī
    0.06
    èĢĮä¸įæĺ¯
    0.06
    Activations Density 0.030%

    No Known Activations