© 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. 19444
    Prev
    Next
    INDEX
    Explanations

    multilingual or mixed-language contexts

    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
    менов
    -0.08
    imit
    -0.08
    -0.07
    roads
    -0.07
    onne
    -0.07
    åĮĸçļĦ
    -0.07
    ä½Ĩä¸į
    -0.07
    ahan
    -0.07
    ụt
    -0.07
    heck
    -0.07
    POSITIVE LOGITS
    воло
    0.07
    åıĬ使çĶ¨
    0.07
    åıĬéĶĢåĶ®
    0.07
    uze
    0.07
    /release
    0.07
    äºĨçĦ¶
    0.06
     بÙħثابة
    0.06
     usual
    0.06
    ÙħÙĴ
    0.06
    ‘s
    0.06
    Activations Density 0.002%

    No Known Activations