© 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. 55582
    Prev
    Next
    INDEX
    Explanations

    district airport railway

    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
    ä¸įå½Ĵ
    -0.09
    erin
    -0.07
    èĩªè¨Ģ
    -0.07
    itational
    -0.07
    er
    -0.07
    ä¸įå¹³
    -0.07
    ä¸Ģåİ»
    -0.07
    å½¢çĬ¶çļĦ
    -0.07
     unbelievable
    -0.07
    ä¸įåı¯æĬĹ
    -0.07
    POSITIVE LOGITS
    Ïĩη
    0.07
    è§Ĵ
    0.07
    èĢĮåĬ¨
    0.07
    ĮĢ
    0.07
    -mobile
    0.07
     Magnes
    0.07
    Ùħاس
    0.07
    详ç»Ĩä¿¡æģ¯
    0.07
    ÙħÙĨت
    0.07
    å¤Ħ
    0.06
    Activations Density 0.002%

    No Known Activations