© 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. 42789
    Prev
    Next
    INDEX
    Explanations

    code, implementations, command

    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
    -ie
    -0.08
    æĢ»ç®¡
    -0.07
    该å±Ģ
    -0.07
    .TryParse
    -0.07
    icity
    -0.06
    shouldBe
    -0.06
    ä»İä¸Ń
    -0.06
    éģĵæĿ¥
    -0.06
    æ¯ĴæĢ§
    -0.06
     requestId
    -0.06
    POSITIVE LOGITS
    éĩĩçĶ¨çļĦæĺ¯
    0.08
    roma
    0.07
    kla
    0.07
    å®ŀéĻħæĵįä½ľ
    0.07
    utzer
    0.07
    amble
    0.07
    ASTER
    0.07
    endan
    0.07
     vist
    0.07
    åľ¨æł¡
    0.07
    Activations Density 0.014%

    No Known Activations