© 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. 8997
    Prev
    Next
    INDEX
    Explanations

    respect to

    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
    åıĮé¾Ļ
    -0.08
    æ¯ıé¢ĺ
    -0.08
    лио
    -0.08
    .*,
    -0.07
    åıĪ称为
    -0.07
    åıĬåħ¶åºĶçĶ¨
    -0.07
    èĽŁ
    -0.07
    æĢ»æľīä¸Ģ天
    -0.07
    atak
    -0.07
    vlc
    -0.07
    POSITIVE LOGITS
    ubern
    0.07
    ezu
    0.07
    ocoder
    0.06
    æĢİä¹Īçľĭ
    0.06
    ä¾Ŀ
    0.06
    ä¸įå¹²
    0.06
     Henn
    0.06
    补足
    0.06
    ↵
    0.06
    ä¸įåĬ¨
    0.06
    Activations Density 0.005%

    No Known Activations