© 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. 18597
    Prev
    Next
    INDEX
    Explanations

    words like Spanish or evening

    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
    dux
    -0.08
     furthermore
    -0.08
     Furthermore
    -0.07
    ç´§åĩij
    -0.07
    ην
    -0.07
    _kwargs
    -0.07
    tijk
    -0.07
    Furthermore
    -0.07
    宫
    -0.07
    åħ®
    -0.07
    POSITIVE LOGITS
    opus
    0.07
    à¸ĺาà¸Ļี
    0.06
    sdale
    0.06
    éĺħè¯»æľ¬æĸĩ
    0.06
     ÙĦذا
    0.06
    ç¼ĸåıij
    0.06
    innen
    0.06
    gets
    0.06
    æĸ°çŁ¥è¯Ĩ
    0.06
     "-
    0.06
    Activations Density 0.017%

    No Known Activations