© 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. 46882
    Prev
    Next
    INDEX
    Explanations

    Q fields mathematical objects

    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
    obie
    -0.08
    å¼Ĥä½į
    -0.08
    rement
    -0.08
     sema
    -0.07
    ogy
    -0.07
    Ñħам
    -0.07
    æ¥ł
    -0.07
    advert
    -0.07
    ÙĪØ®
    -0.07
    gant
    -0.07
    POSITIVE LOGITS
    desk
    0.07
    ütz
    0.07
    åİĨåı²ä¸Ĭ
    0.07
     rational
    0.07
    å°Ķé¡¿
    0.06
    æ·¡
    0.06
    é¦ĸéĥ¨
    0.06
    ran
    0.06
    ç½ijçļĦ
    0.06
    Rare
    0.06
    Activations Density 0.005%

    No Known Activations