© 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. 1161
    Prev
    Next
    INDEX
    Explanations

    numbers following slashes or hyphens

    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
    สร
    -0.07
    çıĬ
    -0.07
    éļ¾æ±Ĥ
    -0.06
    æĸ¯çī¹
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    缨
    -0.06
    istr
    -0.06
    ép
    -0.06
    lessness
    -0.06
    éĩijé¾Ļ
    -0.06
    POSITIVE LOGITS
    ëĤĺë§Ī
    0.08
    oyer
    0.08
    ä¸ĩåįĥ
    0.07
    ãģĹãģıãģ¯
    0.07
    inz
    0.07
    åIJĮæĹ¥
    0.07
    ÑĢое
    0.07
    iono
    0.07
    anken
    0.07
    ANCED
    0.07
    Activations Density 0.410%

    No Known Activations