© 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. 3956
    Prev
    Next
    INDEX
    Explanations

    $SU(3)_C \times SU(2)_L \times U(1)_Y$ fields

    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
    ugu
    -0.07
     ASTM
    -0.07
    ummy
    -0.07
    æ¼ł
    -0.07
    é¦Ļæ²¹
    -0.06
     tol
    -0.06
     fflush
    -0.06
     маÑĪине
    -0.06
    æ·±åIJ¸
    -0.06
     recal
    -0.06
    POSITIVE LOGITS
    æķĻåŃ¦è®¡åĪĴ
    0.08
    blok
    0.08
    åIJĪåĶ±åĽ¢
    0.08
    ientes
    0.08
    allowed
    0.08
    νια
    0.08
    åĴĮä¿ĿæĬ¤
    0.07
    ãĥ«ãĥ¼
    0.07
    æĪIJåijĺçļĦ
    0.07
    ingleton
    0.07
    Activations Density 0.004%

    No Known Activations