© 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. 61761
    Prev
    Next
    INDEX
    Explanations

    resolve function calls and assignments

    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
    ishly
    -0.09
    zul
    -0.09
    arani
    -0.08
    arer
    -0.08
    retty
    -0.08
    arana
    -0.08
    æ´Ľæĸ¯
    -0.08
    enticate
    -0.08
    riage
    -0.08
    dater
    -0.08
    POSITIVE LOGITS
     rÃłng
    0.09
    ä¸įå¼ĢçļĦ
    0.08
    idual
    0.07
    æ±Łå¸Ĥ
    0.07
    بØŃ
    0.07
    ãģĨãģ¡
    0.07
    ä¸įäºĨ
    0.07
     vẹn
    0.07
    irement
    0.07
     ambigu
    0.07
    Activations Density 0.025%

    No Known Activations