© 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. 10415
    Prev
    Next
    INDEX
    Explanations

    time units

    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
    ä»ĸçİ°åľ¨
    -0.10
    ä¸Ģæĸij
    -0.08
    çļĦäºĨ
    -0.08
    ä¸Ĭæĺ¯
    -0.07
    ä¸įä¹±
    -0.07
    .isLoggedIn
    -0.07
    æĹ¥è¡¨ç¤º
    -0.07
    许许å¤ļ
    -0.07
    åIJİè¿Ľè¡Į
    -0.07
    canf
    -0.07
    POSITIVE LOGITS
     totiž
    0.08
     infatti
    0.08
     inilah
    0.08
    à¸Ĺีà¹Ģà¸Ķียว
    0.07
    åĽłæ¶īå«Į
    0.07
     bowiem
    0.07
    åijĹ
    0.07
     unsuccessfully
    0.06
     ugyanis
    0.06
    æĪij们就
    0.06
    Activations Density 0.679%

    No Known Activations