© 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. 42669
    Prev
    Next
    INDEX
    Explanations

    Zhou Dynasty

    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
    èľ¿
    -0.08
     Ustad
    -0.08
     Ons
    -0.07
     Sloan
    -0.07
    ä¸Ģæĭ³
    -0.07
    راج
    -0.07
     McMaster
    -0.07
    éľĦ
    -0.07
    æŀģå°ijæķ°
    -0.07
    disp
    -0.07
    POSITIVE LOGITS
    æĺ¥ç§ĭ
    0.11
    诸侯
    0.10
    龸主
    0.09
    éĿĴéĵľ
    0.08
    æ¥ļåĽ½
    0.08
    æĪĺåĽ½
    0.08
    èĤ¥
    0.08
    大夫
    0.08
    åħ¼å¹¶
    0.08
    åħ¬åħĥåīį
    0.07
    Activations Density 0.006%

    No Known Activations