© 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. 50433
    Prev
    Next
    INDEX
    Explanations

    polynomial degree

    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
    rens
    -0.08
    ÑĪин
    -0.08
    odos
    -0.08
    äºijå±±
    -0.08
    åd
    -0.08
    hei
    -0.08
    qip
    -0.08
    umen
    -0.08
    çīĪæĿĥä¸İåħį责声æĺİ
    -0.08
    åĴĮä¿ĿæĬ¤
    -0.08
    POSITIVE LOGITS
     Weiner
    0.06
    af
    0.06
    lest
    0.06
    ç¥Ŀ
    0.05
     Quadr
    0.05
     gesta
    0.05
    çī¹åľ°
    0.05
     ì§ĵ
    0.05
     stationary
    0.05
    åīį两
    0.05
    Activations Density 0.001%

    No Known Activations