© 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. 33807
    Prev
    Next
    INDEX
    Explanations

    gluon interactions

    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¸ĢæıIJ
    -0.07
    没æľīåĩºçİ°
    -0.07
    DSP
    -0.07
     graduated
    -0.07
     Cod
    -0.07
    ostal
    -0.06
    天干
    -0.06
    coder
    -0.06
    çħ§
    -0.06
    é¡½åĽº
    -0.06
    POSITIVE LOGITS
    ÑĦика
    0.09
    æ±łä¸Ń
    0.08
    ajat
    0.08
    è¾¾æĭī
    0.08
    portun
    0.08
    æ±ł
    0.08
    ä¸Ĭè¡Į
    0.07
    ggi
    0.07
    zek
    0.07
    大峡谷
    0.07
    Activations Density 0.004%

    No Known Activations