© 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. 55520
    Prev
    Next
    INDEX
    Explanations

    mathematical constants and variables

    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
    weis
    -0.07
    ä¿Ŀå®Ī
    -0.07
    æ±Łå±±
    -0.06
    端çĿĢ
    -0.06
    ÙĨد
    -0.06
    æī
    -0.06
    æĢİä¹ĪåĬŀ
    -0.06
    pat
    -0.06
    çĻ¾åIJĪ
    -0.06
    ä¸įå¾Ĺå·²
    -0.06
    POSITIVE LOGITS
    ropolitan
    0.07
    onnée
    0.07
    aniel
    0.07
    æĹħ游度åģĩåĮº
    0.07
    reau
    0.07
    åĭĴ
    0.07
    å¨ĺåŃIJ
    0.07
    ивно
    0.07
    antina
    0.07
    é«ĺæ°Ķ
    0.07
    Activations Density 0.002%

    No Known Activations