© 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. 41385
    Prev
    Next
    INDEX
    Explanations

    van der Waals

    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
    خاÙĨÙĩ
    -0.08
    å½¢å¼ıå¤ļæł·
    -0.07
    cheon
    -0.07
    onda
    -0.07
    forder
    -0.07
     Raya
    -0.07
    tagli
    -0.07
    ondag
    -0.06
    åİŁæ±ģ
    -0.06
    ÑĥкÑĢа
    -0.06
    POSITIVE LOGITS
    éļĪ
    0.07
    æĢ§è´¨çļĦ
    0.07
    æ°ı
    0.07
    èĩªèIJ¥
    0.07
     sno
    0.06
    离æĪij们
    0.06
    reibung
    0.06
     Blasio
    0.06
    hu
    0.06
    à¹īาย
    0.06
    Activations Density 0.003%

    No Known Activations