© 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. 61266
    Prev
    Next
    INDEX
    Explanations

    proximity and containment

    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
    odoro
    -0.08
    çīĪçļĦ
    -0.07
    åīįè¨Ģ
    -0.07
    åľ¨çº¿çķĻè¨Ģ
    -0.07
    ibar
    -0.06
    ero
    -0.06
    ä»ĸçļĦä½ľåĵģ
    -0.06
     otherwise
    -0.06
    erop
    -0.06
    ïs
    -0.06
    POSITIVE LOGITS
    ç¼ķ
    0.08
     olev
    0.08
    stående
    0.08
    ãģŁãĤĭ
    0.08
    лежа
    0.07
    æĪĸ缴æİ¥
    0.07
    ding
    0.07
    inna
    0.07
    /current
    0.07
    ä¹ĭä¸ĢçļĦ
    0.07
    Activations Density 0.177%

    No Known Activations