© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49896
    Prev
    Next
    INDEX
    Explanations

    quantities and ratios

    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
    utul
    -0.07
    LBL
    -0.07
    æ³
    -0.07
    æĶ¶å®ĺ
    -0.07
    ä¸įå¦Ĥ
    -0.07
    kens
    -0.07
    Attrs
    -0.06
     beginners
    -0.06
    çļĦåħ¨æĸ°
    -0.06
    วà¸Ķ
    -0.06
    POSITIVE LOGITS
     tzw
    0.08
    导
    0.08
    综åIJĪ
    0.07
    åĨĻåĪ°
    0.07
     squared
    0.07
     integrated
    0.07
    æŁIJç§į
    0.07
    åĢĴæķ°
    0.07
     sogenannten
    0.07
    综
    0.07
    Activations Density 0.024%

    No Known Activations