© 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. 34151
    Prev
    Next
    INDEX
    Explanations

    code execution and method calls

    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
    osp
    -0.08
     Cott
    -0.07
    .gstatic
    -0.07
    oland
    -0.07
    verte
    -0.07
    ĤŃ
    -0.07
    زÙĨ
    -0.07
    å¥
    -0.07
    ÙĥÙĪر
    -0.06
    红å¤ĸ
    -0.06
    POSITIVE LOGITS
    .prepare
    0.07
     Sohn
    0.07
    fact
    0.07
    sembl
    0.07
    ä¸Ģå®ļéĩıçļĦ
    0.07
    venuto
    0.06
    hões
    0.06
    ergency
    0.06
    æĪijæĦ¿æĦı
    0.06
     Special
    0.06
    Activations Density 0.021%

    No Known Activations