© 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. 28834
    Prev
    Next
    INDEX
    Explanations

    numbers followed by names or codes

    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
    :description
    -0.06
    orrow
    -0.06
    _der
    -0.06
    íĺ¹
    -0.06
    ä¾Ŀæ³ķ追究责任
    -0.06
    /the
    -0.06
    ancio
    -0.06
    istre
    -0.06
    istr
    -0.06
     LoggerFactory
    -0.06
    POSITIVE LOGITS
    ADED
    0.07
    estand
    0.07
    åĬłæĭ¿å¤§
    0.07
    ENDOR
    0.07
    æĸ°åĬłåĿ¡
    0.07
    俱ä¹IJéĥ¨
    0.07
    欢è¿İ广大
    0.07
    øb
    0.07
    人家
    0.07
    éĺ¿æĭī伯
    0.07
    Activations Density 0.033%

    No Known Activations