© 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. 65187
    Prev
    Next
    INDEX
    Explanations

    (R) or chemical symbols

    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
    å¾ĹäºĨ
    -0.07
    Ñĥдо
    -0.06
    ä»Ģä¹Īåij¢
    -0.06
    å®ģå¸Ĥ
    -0.06
    áŁĥ
    -0.06
    -sama
    -0.06
    matic
    -0.06
    个åŃ©åŃIJ
    -0.06
    ä¿Ŀå®Ī
    -0.06
    é¢ĿçļĦ
    -0.06
    POSITIVE LOGITS
    ugin
    0.08
    ãģ¾ãģ¾
    0.08
    ald
    0.07
    ujourd
    0.07
    orej
    0.07
    atrice
    0.07
    æĸ°å®ī
    0.07
     espont
    0.07
    ponible
    0.07
    æŶéļĶ
    0.07
    Activations Density 0.003%

    No Known Activations