© 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. 29631
    Prev
    Next
    INDEX
    Explanations

    particular in, addition to, dumpster size

    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
     Opin
    -0.07
    æĭĨè¿ģè¡¥åģ¿
    -0.07
    è¡Įä¸ļèµĦ讯
    -0.06
    èĮĦåŃIJ
    -0.06
     Utre
    -0.06
    .nasa
    -0.06
    ero
    -0.06
    ibs
    -0.06
     Radi
    -0.06
    èĩªå·²
    -0.06
    POSITIVE LOGITS
    ä¸ĭåĪĹåħ³äºİ
    0.07
    voud
    0.07
    åľ
    0.07
    æ³ķæĺ¯
    0.07
    çľī
    0.07
    èľ
    0.07
     непÑĢе
    0.07
    樽
    0.07
    ARC
    0.07
    rende
    0.07
    Activations Density 0.001%

    No Known Activations