© 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. 48872
    Prev
    Next
    INDEX
    Explanations

    sentence endings punctuation

    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
    åĩ
    -0.08
    çļĦå¿ĥæĢĿ
    -0.07
    æĮīçIJĨ
    -0.07
    åıªè¦ģä¸Ģ
    -0.07
    éŨæĪ·ç½ijç«Ļ
    -0.07
    çĩ¥
    -0.07
    abaj
    -0.06
    ä¹ĭ计
    -0.06
    ouer
    -0.06
    ourg
    -0.06
    POSITIVE LOGITS
    æ·Ģ
    0.08
    ¼
    0.07
    stadt
    0.07
     Interesting
    0.07
    è²Ĥ
    0.07
     Useful
    0.07
     interesting
    0.07
    ita
    0.07
    uzu
    0.07
    éľĢ注æĦı
    0.06
    Activations Density 0.021%

    No Known Activations