© 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. 21081
    Prev
    Next
    INDEX
    Explanations

    railbound vehicles

    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
    eih
    -0.07
    ä¸ĸå¤ĸ
    -0.07
    ocking
    -0.07
    /we
    -0.06
    (es
    -0.06
     esp
    -0.06
    ught
    -0.06
     Esp
    -0.06
    åĭĴæĸ¯
    -0.06
    à¹Ģล
    -0.06
    POSITIVE LOGITS
    appel
    0.07
    ÃīR
    0.07
    -pass
    0.07
    åľ¨ä»¥åIJİ
    0.07
     drown
    0.07
    ç«Ļ起身
    0.07
    icen
    0.07
    å§ĭç»Īä¿ĿæĮģ
    0.06
    åľ¨ä¸Ĭè¿°
    0.06
    å°ģ
    0.06
    Activations Density 1.350%

    No Known Activations