© 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. 9271
    Prev
    Next
    INDEX
    Explanations

    moving, decide, real, cost

    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
    odo
    -0.08
    æĹłéĿŀ
    -0.07
    ãģ¨ãģĦãģĪãģ°
    -0.07
    ×IJ×Ļ
    -0.07
    åIJĦä¸ĵä¸ļ
    -0.07
    é£İæĻ¯çº¿
    -0.07
    ceso
    -0.07
    agus
    -0.07
    cob
    -0.07
     RATE
    -0.06
    POSITIVE LOGITS
    æŁ¥çľĭåħ¨æĸĩ
    0.07
    CISION
    0.07
    å¤įåĪ¶éĵ¾æİ¥
    0.07
    uston
    0.07
    æīĢåIJij
    0.07
     ev
    0.07
    ObjectName
    0.07
    åĭĻ
    0.06
    ãĤ¸ãĤª
    0.06
    ç³
    0.06
    Activations Density 0.012%

    No Known Activations