© 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. 56008
    Prev
    Next
    INDEX
    Explanations

    having

    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
    zilla
    -0.09
    翼翼
    -0.09
    rito
    -0.08
    ì¦IJ
    -0.07
    å¤©æľº
    -0.07
    jenigen
    -0.07
    quÃŃ
    -0.07
    ction
    -0.07
    ä¸ĢåĽŀäºĭ
    -0.07
    è¦ĭãģ¤
    -0.07
    POSITIVE LOGITS
    s
    0.10
    代表æĢ§çļĦ
    0.10
    æĺİæĺ¾çļĦ
    0.10
    ات
    0.09
    ×Ļ×Ŀ
    0.08
    çİ°åľ¨æĪij们
    0.08
    onne
    0.08
    缸åIJĮçļĦ
    0.07
    allery
    0.07
    es
    0.07
    Activations Density 0.005%

    No Known Activations