© 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. 27486
    Prev
    Next
    INDEX
    Explanations

    sentence start words

    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
    说æĺİ
    -0.08
    unno
    -0.08
    æ¸ł
    -0.08
    ipan
    -0.07
    uban
    -0.07
    rets
    -0.07
    اÙģ
    -0.07
     cie
    -0.07
    à§ģর
    -0.07
    ä¸Ĭè¿°äºĭå®ŀ
    -0.07
    POSITIVE LOGITS
    assi
    0.07
    IDGE
    0.07
    天å®ĩ
    0.07
    好åIJĹ
    0.07
    å¥½åľ¨
    0.07
    çĶļèĩ³æ¯Ķ
    0.07
     Mendoza
    0.06
    éĿŀ常æĸ¹ä¾¿
    0.06
    еÑĨ
    0.06
    åİ»çİ©
    0.06
    Activations Density 0.052%

    No Known Activations