© 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. 56826
    Prev
    Next
    INDEX
    Explanations

    dates or numbers

    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
    ügen
    -0.07
    欢è¿İæĤ¨
    -0.07
    åĪĨãģij
    -0.06
    é»Ħé¾Ļ
    -0.06
    bish
    -0.06
     Diri
    -0.06
    æĬĺä¸į
    -0.06
    visor
    -0.06
    ByText
    -0.06
    æĸ°æµªè´¢ç»ı
    -0.06
    POSITIVE LOGITS
    ena
    0.07
    Öĩ
    0.07
     Pod
    0.06
    æİĸ
    0.06
    ouw
    0.06
     LOT
    0.06
    åĴĮçĪ¶æ¯į
    0.06
    ãĢįãĢĮ
    0.06
    erne
    0.06
    aler
    0.06
    Activations Density 0.002%

    No Known Activations