© 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. 7626
    Prev
    Next
    INDEX
    Explanations

    because of

    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
     mos
    -0.08
    oló
    -0.08
     Tá
    -0.07
    æ°¸è¿ľçļĦ
    -0.07
    ór
    -0.07
    bió
    -0.07
    ó
    -0.07
    óx
    -0.07
    _SENT
    -0.06
    æĪij以为
    -0.06
    POSITIVE LOGITS
    æĹłéĿŀ
    0.11
    enius
    0.09
    ade
    0.08
    æĺ¯ä½ķ
    0.07
    ä»ĸ们éĥ½æĺ¯
    0.07
    à¸īะà¸Ļัà¹īà¸Ļ
    0.07
    æīĢå¤ĦçļĦ
    0.07
    çļĨæĺ¯
    0.07
    æľ¬è´¨
    0.07
     intervening
    0.07
    Activations Density 0.010%

    No Known Activations