© 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. 18656
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and models

    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
    ðŁĻĤ
    -0.08
    faker
    -0.08
    erman
    -0.08
     wirk
    -0.08
    åºĨç¥Ŀä¸ŃåĽ½åħ±äº§åħļæĪIJç«ĭ
    -0.07
    èѦéĴŁ
    -0.07
    adrid
    -0.07
    çĸ®
    -0.07
    asename
    -0.07
    æĺ¯ä½ķåIJ«ä¹ī
    -0.07
    POSITIVE LOGITS
    çIJĨ论ä¸Ĭ
    0.11
     theoretically
    0.10
     theoretical
    0.10
     formulas
    0.10
     mathematical
    0.08
    çIJĨè®ºçŁ¥è¯Ĩ
    0.08
    åħ¬å¼ı
    0.08
    çIJĨè®ºåŁºç¡Ģ
    0.08
    æķ°åѦ
    0.08
     theoret
    0.08
    Activations Density 0.111%

    No Known Activations