© 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. 21822
    Prev
    Next
    INDEX
    Explanations

    river banks

    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
    ç¥ĸ
    -0.06
     unre
    -0.06
    åıĸèĩª
    -0.05
    å¸ĤæĶ¿å·¥ç¨ĭ
    -0.05
    ake
    -0.05
    èĩªå·±éĥ½
    -0.05
    kep
    -0.05
    çĤ¹åIJİ
    -0.05
    urgo
    -0.05
     miner
    -0.05
    POSITIVE LOGITS
    沿线
    0.08
    .side
    0.08
     lẻ
    0.08
    anski
    0.08
    é´¨
    0.08
    quist
    0.08
    æĹģ
    0.08
    ippi
    0.08
    สาย
    0.08
     Trilogy
    0.08
    Activations Density 0.197%

    No Known Activations