© 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. 50896
    Prev
    Next
    INDEX
    Explanations

    mixed or different

    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
    ׼×Ķ
    -0.07
    åı°åīį
    -0.07
    ¾
    -0.06
     am
    -0.06
    ain
    -0.06
    éĢıè¿ĩ
    -0.06
    æĬķåħ¥
    -0.06
     mob
    -0.06
    czy
    -0.06
    ctype
    -0.06
    POSITIVE LOGITS
    ä¸įåIJĮçļĦ人
    0.18
    ä¸įåIJĮçļĦ
    0.17
    åľ¨ä¸įåIJĮçļĦ
    0.17
    different
    0.17
     different
    0.16
    对ä¸įåIJĮ
    0.15
    ä¸įåIJĮ
    0.15
    åľ¨ä¸įåIJĮ
    0.15
    çļĦä¸įåIJĮ
    0.15
    çķ°ãģªãĤĭ
    0.15
    Activations Density 0.193%

    No Known Activations