© 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. 61601
    Prev
    Next
    INDEX
    Explanations

    view, TreeNode, -books, CPU, lt

    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
    ÑĪив
    -0.06
    Õ¸ÖĤÕ¶
    -0.06
     micro
    -0.06
    lesh
    -0.06
    rika
    -0.06
    Äįi
    -0.06
    æĥ³è±¡ä¸ŃçļĦ
    -0.06
    urons
    -0.06
    ura
    -0.05
    æĿ¥èĩª
    -0.05
    POSITIVE LOGITS
    еÑĩе
    0.08
     distanci
    0.08
    åľ¨éŁ©åĽ½
    0.08
    OLER
    0.07
    ophon
    0.07
     prést
    0.07
    lá
    0.07
    èĢĮ代ä¹ĭ
    0.07
    ë¡Ģ
    0.07
    åħ¨è¿ĩç¨ĭ
    0.07
    Activations Density 0.090%

    No Known Activations