© 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. 18805
    Prev
    Next
    INDEX
    Explanations

    dates and titles

    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
    æĵį
    -0.08
    ä»»ä½ķä¸Ģ个
    -0.07
    åºı
    -0.07
    cese
    -0.06
    ooter
    -0.06
    ئÙĨ
    -0.06
    enom
    -0.06
    iston
    -0.06
    æĺ¯ä¸Ģç§įéĿŀ常
    -0.06
    çĦ¶åIJİåĨį
    -0.06
    POSITIVE LOGITS
     indirectly
    0.08
    æĿ¥èĩª
    0.08
     provenienti
    0.07
    ä¾Ĩèĩª
    0.07
     valign
    0.07
    å°¾
    0.07
     junto
    0.07
    avid
    0.07
    รà¹Īวมà¸ģัà¸ļ
    0.07
    arbeiter
    0.07
    Activations Density 0.039%

    No Known Activations