© 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. 46639
    Prev
    Next
    INDEX
    Explanations

    material or contents

    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
    ä¾Ĩèĩª
    -0.08
    å°ijèµ°
    -0.07
    æĿ¥èĩª
    -0.07
    timi
    -0.07
    æºIJåľ°
    -0.07
    è¿ľæĸ¹çļĦ
    -0.07
     rel
    -0.07
    utnik
    -0.07
    éģ¥è¿ľ
    -0.07
    è©®
    -0.06
    POSITIVE LOGITS
    éĻĦçĿĢ
    0.09
    éĻĦå±ŀ
    0.09
    ä¾ĿéĻĦ
    0.09
    ovable
    0.08
    /original
    0.08
     movable
    0.08
    å®Įå·¥
    0.08
    åĬ¨äº§
    0.08
    æĪIJæĸ°
    0.08
     improvements
    0.08
    Activations Density 0.017%

    No Known Activations