© 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. 3030
    Prev
    Next
    INDEX
    Explanations

    produced electrons

    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
    åħ¶è§ĤçĤ¹
    -0.08
     clutter
    -0.08
     trÃłn
    -0.08
    èĸ°
    -0.08
    ÛĮØ´Ùĩ
    -0.08
     cong
    -0.07
    odie
    -0.07
    endar
    -0.07
    æĭ¥
    -0.07
    åīĶéĻ¤
    -0.07
    POSITIVE LOGITS
     electrons
    0.07
    åıĤä¸İçļĦ
    0.07
     shed
    0.07
    åĮĸåIJĪ
    0.07
    éĢĨ转
    0.07
    æĢ»åħ±
    0.07
    lost
    0.07
    为使
    0.07
    åıĤä¸İ
    0.07
     shedding
    0.07
    Activations Density 0.001%

    No Known Activations