© 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. 40898
    Prev
    Next
    INDEX
    Explanations

    equals sign

    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
    é¸ŃèĽĭ
    -0.07
    -0.07
    Ù
    -0.07
    æĤłæĤł
    -0.07
    åıĤä¼ļ人åijĺ
    -0.06
    elar
    -0.06
    ä¸įçĪ½
    -0.06
    intValue
    -0.06
     value
    -0.06
    èĢĮæĺ¯è¦ģ
    -0.06
    POSITIVE LOGITS
    lop
    0.08
     ========
    0.08
    ầm
    0.08
    ìĹŃìĿĦ
    0.07
    chron
    0.07
    äºĭåħ³
    0.07
    产åĵģä»·æł¼
    0.07
    产åĵģåĴĮ
    0.07
    åĭ¿æī°
    0.07
    æľīåı²
    0.07
    Activations Density 0.011%

    No Known Activations