© 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. 32679
    Prev
    Next
    INDEX
    Explanations

    not admitted prior art

    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
    ."',
    -0.09
    뢰
    -0.08
    alled
    -0.08
    ãģĹãģı
    -0.08
    åı¸
    -0.07
    caria
    -0.07
    å´©
    -0.07
    loid
    -0.07
    æĮº
    -0.07
     mos
    -0.07
    POSITIVE LOGITS
    åľ¨ä»¥åIJİ
    0.07
    以任ä½ķ
    0.07
     Jacobs
    0.07
    åĪ°è¿ĩ
    0.06
    é¼ĵåĬ±åĴĮ
    0.06
    imis
    0.06
     нико
    0.06
    scp
    0.06
    enumer
    0.06
     encompasses
    0.06
    Activations Density 0.085%

    No Known Activations