© 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. 15607
    Prev
    Next
    INDEX
    Explanations

    positive definite

    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
    ewis
    -0.07
    顺
    -0.07
    éłĨ
    -0.07
    éĢĨè¡Į
    -0.07
    atile
    -0.07
    导åIJij
    -0.07
    avian
    -0.07
    epass
    -0.07
    avig
    -0.07
    ew
    -0.07
    POSITIVE LOGITS
    rone
    0.08
    ัà¸ķ
    0.08
    ä¸įæĩĪ
    0.08
    ä¸ĢéĴĪ
    0.07
    磫
    0.07
     unless
    0.07
    éĻ¤éĿŀ
    0.07
    ä¸įåı¯æĽ¿ä»£
    0.07
    Unless
    0.07
    zis
    0.07
    Activations Density 0.003%

    No Known Activations