© 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. 49114
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and statistics

    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
    èĮ«èĮ«
    -0.06
    éĢĬ
    -0.06
    èµĦæĸĻ
    -0.06
    /
    -0.06
    å°ıçĨĬ
    -0.06
    aldo
    -0.06
    -
    -0.06
    èµĦæĸĻåĴĮ
    -0.05
    驯
    -0.05
    burg
    -0.05
    POSITIVE LOGITS
    ä¸İçİ°å®ŀ
    0.08
    .ir
    0.08
    ctors
    0.08
    ç¬Ķä¸ĭçļĦ
    0.08
    plet
    0.08
    plets
    0.08
    åķ¤
    0.07
    á»Ļc
    0.07
    nyi
    0.07
    çŃīåįķä½į
    0.07
    Activations Density 0.002%

    No Known Activations