© 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. 51790
    Prev
    Next
    INDEX
    Explanations

    closing punctuation followed by 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
    èĩªèº«çļĦ
    -0.07
    perm
    -0.07
    ä¸Ģæĸ¹éĿ¢
    -0.07
    klus
    -0.07
    باد
    -0.07
    _cs
    -0.07
    æĺĻ
    -0.06
    idik
    -0.06
    Ele
    -0.06
    æ¯ķ
    -0.06
    POSITIVE LOGITS
    ãģĦãģļãĤĮ
    0.11
    æĢ»ä¹ĭ
    0.10
    åIJİèĢħ
    0.09
     whichever
    0.09
    两èĢħ
    0.08
    éĥ½è¡Į
    0.08
    ãģ©ãģ¡ãĤīãĤĤ
    0.08
    èĩ¥
    0.08
    ichever
    0.08
     latter
    0.08
    Activations Density 0.128%

    No Known Activations