© 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. 15066
    Prev
    Next
    INDEX
    Explanations

    position in text

    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
    uzzi
    -0.08
    iman
    -0.07
    inson
    -0.07
    æĥħåĨµè¯´æĺİ
    -0.07
    *\
    -0.07
    è¿Ļä¹Ī说
    -0.07
    awa
    -0.07
    大æĬĬ
    -0.07
    ennen
    -0.07
    èī¶
    -0.07
    POSITIVE LOGITS
    ç¬¬åĽĽä¸ª
    0.07
    çļĦ第
    0.07
    ilon
    0.07
    ç¬¬åĽĽåŃ£
    0.07
    æİĴåIJį第
    0.07
    第
    0.07
    è¶ĬæĿ¥è¶Ĭè¿ij
    0.07
    ¬ģ
    0.07
    RoleId
    0.07
    åĴĮ游æĪı
    0.06
    Activations Density 0.469%

    No Known Activations