© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14745
    Prev
    Next
    INDEX
    Explanations

    complex mathematical expressions

    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
    ãģ¨ãģĦãģĨãģ¨
    -0.09
    æ¯ıä¸Ģ个åѦçĶŁ
    -0.09
    Ł
    -0.08
    _>
    -0.08
    åī¯åİħéķ¿
    -0.08
    åī¯ä¼ļéķ¿
    -0.08
    ä»Ģä¹Īåij¢
    -0.08
    åѦéĻ¢éĻ¢éķ¿
    -0.08
    ãģ¨ãģĦãģĪãģ°
    -0.08
    addir
    -0.08
    POSITIVE LOGITS
    ãģ¬
    0.07
    梦幻
    0.07
    æľ«
    0.06
    uchu
    0.06
    ledo
    0.06
    æĬĹ
    0.06
    uplic
    0.06
     fisc
    0.06
    ucc
    0.06
    quée
    0.06
    Activations Density 0.035%

    No Known Activations