© 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. 31744
    Prev
    Next
    INDEX
    Explanations

    filed petition

    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
    å¾Ĺåĥı
    -0.08
     sometimes
    -0.07
    æľīæŶåĢĻ
    -0.07
    è¿ĻåĦ¿
    -0.06
    ä½łå¾Ĺ
    -0.06
    å¹´å¹´
    -0.06
     "
    -0.06
    tü
    -0.06
     thousands
    -0.06
    ä½łåı¯èĥ½ä¼ļ
    -0.06
    POSITIVE LOGITS
    æľªåľ¨
    0.08
    -caption
    0.08
    å¯¹æľ¬æ¬¡
    0.08
     intim
    0.08
     substantive
    0.08
    èĩªçŁ¥
    0.08
    æĿIJæĸĻåıĬ
    0.08
    ÙĪبÙĬ
    0.07
    ä¸įæŀĦæĪIJ
    0.07
    æľ¬æ¡Ī
    0.07
    Activations Density 0.090%

    No Known Activations