© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 33087
    Prev
    Next
    INDEX
    Explanations

    OfWeek; Slovenia; arter; Short; www.google

    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
     onDataChange
    -0.07
    .getvalue
    -0.07
    exels
    -0.07
    Hotline
    -0.07
    WebResponse
    -0.07
     terpent
    -0.06
    Ø·ÙĪÙħ
    -0.06
    çī¹æĸ¯
    -0.06
     setBackgroundImage
    -0.06
    ÑĤÑĮе
    -0.06
    POSITIVE LOGITS
    оÑĢдина
    0.06
    å¹¼ç¨ļ
    0.06
     Donetsk
    0.06
     اÙĦشاعر
    0.06
     tokoh
    0.05
    ç«ĭç§ĭ
    0.05
    åĪ¤æĸŃé¢ĺ
    0.05
    .prepend
    0.05
     اÙĦÙħتØŃدث
    0.05
     اÙĦشعبÙĬ
    0.05
    Activations Density 10.216%

    No Known Activations