© 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. 58422
    Prev
    Next
    INDEX
    Explanations

    together, linking, accompanying

    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
    éch
    -0.08
    osu
    -0.08
    æŁIJ天
    -0.08
    ä½ķåľ°
    -0.07
    å¤ļæĸ¹
    -0.07
    OPA
    -0.07
    è
    -0.07
    eel
    -0.07
    UIL
    -0.07
    æĿ¡æĿ¡
    -0.07
    POSITIVE LOGITS
    çĽ¸ä¼´
    0.16
    éħįå¥Ĺ
    0.15
    缸éļı
    0.15
     together
    0.15
    ä¸ĢåIJĮ
    0.14
    ä¸Ģèµ·
    0.14
    è¿ŀ带
    0.14
    ä¸Ģç·Ĵãģ«
    0.14
     accompanying
    0.13
    åľ¨ä¸Ģèµ·çļĦ
    0.13
    Activations Density 0.216%

    No Known Activations