© 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. 41720
    Prev
    Next
    INDEX
    Explanations

    uses cookies

    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
    çī¹åĪ«æĺ¯
    -0.07
    WithOptions
    -0.07
    ured
    -0.06
    æľ¬æ¡Īä¸Ń
    -0.06
    vey
    -0.06
    éĩįçĤ¹ä»»åĬ¡
    -0.06
    ÙĥÙĨ
    -0.06
    åĹ¡åĹ¡
    -0.06
    uring
    -0.06
    ibilit
    -0.06
    POSITIVE LOGITS
    è¿Ļç§įæĸ¹å¼ı
    0.09
     principles
    0.09
    æŶéĹ´æĿ¥
    0.08
     principios
    0.08
    çĶ¨çļĦæĺ¯
    0.08
    outh
    0.07
    èĩªæľīèµĦéĩij
    0.07
    两ç§įæĸ¹å¼ı
    0.07
     hyvä
    0.07
    以ä¸ĭæĸ¹å¼ı
    0.07
    Activations Density 0.101%

    No Known Activations