© 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. 63870
    Prev
    Next
    INDEX
    Explanations

    round to decimal places

    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
     Trev
    -0.07
    enne
    -0.07
    ocs
    -0.07
    ierge
    -0.07
    éĥ½ä¸įçĶ¨
    -0.07
    åĬŀçļĦ
    -0.07
    hô
    -0.07
    Ñİ
    -0.07
    ä½łå°Ĩ
    -0.07
    ç§ijæĬĢåıijå±ķæľīéĻIJåħ¬åı¸
    -0.07
    POSITIVE LOGITS
    oroz
    0.08
    éĢ¢
    0.07
    æĽ¼
    0.07
    ³
    0.07
    éĿ¡
    0.07
    èĶĵ
    0.07
    aktır
    0.07
    leun
    0.07
    è¨Ģ
    0.07
    åĶIJ人
    0.07
    Activations Density 0.327%

    No Known Activations