© 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. 22645
    Prev
    Next
    INDEX
    Explanations

    accuracy and prediction quality

    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
    åĴ½
    -0.07
    æłı
    -0.07
    æľīåĪ©äºİ
    -0.07
    æŀĹåĩ¡
    -0.07
    _FORCE
    -0.07
    åı¯éļıæŶ
    -0.07
    Æ¡i
    -0.07
    laki
    -0.07
    _SAMPL
    -0.07
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.07
    POSITIVE LOGITS
     accuracy
    0.15
    åĩĨç¡®æĢ§
    0.14
    accuracy
    0.13
     Accuracy
    0.13
    误差
    0.12
    Accuracy
    0.12
    ä¸İå®ŀéĻħ
    0.11
    åĩĨ确度
    0.11
    åĩĨç¡®æĢ§åĴĮ
    0.11
     accurate
    0.11
    Activations Density 0.081%

    No Known Activations