© 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. 3975
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and variables

    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
    ä¸ĢåłĤ
    -0.07
    æĥ³æĿ¥
    -0.07
    سا
    -0.07
    eres
    -0.07
    .tom
    -0.07
    ANDROID
    -0.07
    Õ¡Öģ
    -0.07
    Deserializer
    -0.07
    åľ¨çĶŁæ´»ä¸Ń
    -0.07
    åľ¨ä»»ä½ķ
    -0.07
    POSITIVE LOGITS
    令ä»ĸ
    0.07
    iliz
    0.07
    æģ©æĸ¯
    0.06
     med
    0.06
    å°¼å°Ķ
    0.06
    ìĹ°
    0.06
    à¹Ģรียà¸ļ
    0.06
    _SIGN
    0.06
    éĢļäºĨ
    0.06
    å°ıå¿ĥ
    0.06
    Activations Density 0.031%

    No Known Activations