© 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. 62118
    Prev
    Next
    INDEX
    Explanations

    container expansion

    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
    æľ±åħĥ
    -0.08
    ernet
    -0.08
    ä¸įèĭŁ
    -0.07
    ANCH
    -0.07
    ovin
    -0.07
     Ø¥Ùħا
    -0.07
    åħ¨ä¹¡
    -0.07
    缴æİ¥æĪĸ
    -0.06
    ersatz
    -0.06
    ä¸įçŁ¥æīĢ
    -0.06
    POSITIVE LOGITS
    æ¿
    0.08
     wide
    0.07
     vare
    0.07
    ç¼ĵ
    0.07
    arat
    0.07
    olon
    0.07
    大åı¯
    0.07
    unan
    0.07
    åħģ许
    0.07
    ä¸Ģ对ä¸Ģ
    0.07
    Activations Density 0.026%

    No Known Activations