© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17808
    Prev
    Next
    INDEX
    Explanations

    begin or start

    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
    çľ¼ä¸ĭ
    -0.07
    ä¸ĢæŶ
    -0.07
    åħįè´¹åıijå¸ĥ
    -0.07
     recent
    -0.07
    è¿ijæĿ¥
    -0.07
    æĿ¥ä¹ĭ
    -0.06
    landers
    -0.06
    recent
    -0.06
    Chance
    -0.06
    æĬĢæľ¯åıĬ
    -0.06
    POSITIVE LOGITS
    å¼Ģå§ĭ
    0.14
     begin
    0.14
     begins
    0.14
    çļĦå¼Ģå§ĭ
    0.13
    并å¼Ģå§ĭ
    0.13
     Begin
    0.13
     began
    0.13
     begonnen
    0.13
    æľĪ份å¼Ģå§ĭ
    0.13
     starts
    0.13
    Activations Density 0.422%

    No Known Activations