© 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. 13597
    Prev
    Next
    INDEX
    Explanations

    numbers and symbols

    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
    iji
    -0.07
    �
    -0.07
    èµ·åĬ¨
    -0.07
    ctp
    -0.07
    رÙģ
    -0.06
    udel
    -0.06
     {_
    -0.06
    赤åŃĹ
    -0.06
    æŃ£å¥½
    -0.06
    finite
    -0.06
    POSITIVE LOGITS
    微信æī«ä¸Ģæī«
    0.09
    è®´
    0.07
     FOREIGN
    0.07
    é»İæĺİ
    0.07
    ovati
    0.07
    次éĺħ读
    0.07
    éĺħ读åħ¨æĸĩ
    0.07
    æīĭæľºçīĪ
    0.07
    è¿Ļ个åIJįåŃĹåľ¨åĽ½å¤ĸ
    0.07
    INGTON
    0.07
    Activations Density 0.102%

    No Known Activations