© 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. 45180
    Prev
    Next
    INDEX
    Explanations

    specialized academic and scientific terminology

    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
    ç¦ıçī¹
    -0.07
    å¸ĤåľºçĽijçĿ£ç®¡çIJĨæĢ»å±Ģ
    -0.07
    -ever
    -0.07
     archiv
    -0.07
    érés
    -0.07
    inode
    -0.07
    iren
    -0.07
    æ·±åĪ»çļĦåį°è±¡
    -0.07
    irez
    -0.07
     sou
    -0.07
    POSITIVE LOGITS
    æľ¯è¯Ń
    0.09
     details
    0.08
     terminology
    0.08
    ç»ĨèĬĤ
    0.08
     detail
    0.07
    詳細
    0.07
    -level
    0.07
     technical
    0.07
     اÙĦÙħتخصصة
    0.07
    åħĪè¾Ī
    0.07
    Activations Density 0.012%

    No Known Activations