© 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. 26719
    Prev
    Next
    INDEX
    Explanations

    mathematical inequalities and ranges

    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
    æ³½æ°ij
    -0.08
    夺
    -0.07
    æĢ¨
    -0.07
    æ¹
    -0.07
    intis
    -0.07
    ä¼ļåĬ¡
    -0.07
     ÐŃкономи
    -0.07
     lagun
    -0.07
    oyer
    -0.07
    ñas
    -0.07
    POSITIVE LOGITS
     inequalities
    0.10
     inequality
    0.10
    ä¸įçŃī
    0.09
     неÑĢа
    0.09
    _ranges
    0.08
    plex
    0.07
    Ranges
    0.07
    .threshold
    0.07
    éĶĭèĬĴ
    0.07
    æĮģç»ŃæŶéĹ´
    0.07
    Activations Density 0.010%

    No Known Activations