© 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. 38024
    Prev
    Next
    INDEX
    Explanations

    document sections

    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
    -0.07
    èĿ
    -0.07
    +xml
    -0.07
    ogui
    -0.07
    erox
    -0.07
    mailer
    -0.07
    برا
    -0.07
    رساÙĦ
    -0.07
    idik
    -0.07
    åľ°åĪ©
    -0.07
    POSITIVE LOGITS
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.09
    åĽ½å®¶åĴĮåľ°åĮº
    0.07
     uns
    0.07
    åIJijèį£
    0.07
    åıijå±ķæĸ°
    0.07
    ä¹ĭä¸ī
    0.06
    ProductName
    0.06
    kanie
    0.06
    वान
    0.06
    çĤ¹åĪ°
    0.06
    Activations Density 0.009%

    No Known Activations