© 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. 18381
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and variables

    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
    身ä¸Ĭä¸ĭ
    -0.08
     terce
    -0.08
    emui
    -0.08
    æķĻ主
    -0.08
    ارÙĬÙĨ
    -0.08
    auté
    -0.08
    Ñģловно
    -0.08
    ÑħодиÑĤе
    -0.08
    avais
    -0.08
    artig
    -0.08
    POSITIVE LOGITS
    âĢ
    0.08
    ¯
    0.06
    inning
    0.06
    ��
    0.06
    o
    0.06
    ilk
    0.06
    æłı
    0.06
    æŁĦ
    0.06
    z
    0.06
    N
    0.06
    Activations Density 0.028%

    No Known Activations