© 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. 25777
    Prev
    Next
    INDEX
    Explanations

    poly(

    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
    翼翼
    -0.08
    lou
    -0.07
    åĿ
    -0.07
    jol
    -0.07
    /il
    -0.07
    obat
    -0.07
    æ¸Ń
    -0.06
    (/[
    -0.06
    jid
    -0.06
    羯
    -0.06
    POSITIVE LOGITS
    indow
    0.08
    ære
    0.08
    ries
    0.07
    欢è¿İéĺħ读
    0.07
    äºĨä¸Ģå±Ĥ
    0.07
    omy
    0.07
    Whatever
    0.07
    ÙĪÙħات
    0.07
    åįİè¯ŀ
    0.07
    onen
    0.07
    Activations Density 0.038%

    No Known Activations