© 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. 20696
    Prev
    Next
    INDEX
    Explanations

    Python list array operations

    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
    ogn
    -0.07
    åĬĽæ±Ĥ
    -0.06
    ed
    -0.06
    JD
    -0.06
    被人们
    -0.06
    ä¸ĢæĹ¦è¢«
    -0.06
    é¦ĸåħĪéľĢè¦ģ
    -0.06
    ÙħاÙĦ
    -0.06
    elow
    -0.06
    -build
    -0.06
    POSITIVE LOGITS
    幸ç¦ıå¿«ä¹IJ
    0.08
     ÑģÑĤало
    0.08
    riba
    0.08
     trailed
    0.07
     Quer
    0.07
    æ»ĵ
    0.07
    åı¯æĥ³èĢĮçŁ¥
    0.07
    leftright
    0.07
    ä¸ĭä¸ĢåĢĭ
    0.07
    èĮħ
    0.07
    Activations Density 0.013%

    No Known Activations