© 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. 39514
    Prev
    Next
    INDEX
    Explanations

    only, percent, five, three, about

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.09
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.09
    缴æİ¥åIJij
    -0.08
    èĩ³å°ijæľī
    -0.08
    æĪĸå¤ļ个
    -0.08
    enty
    -0.08
    ãģłãģijãģ§ãĤĤ
    -0.08
    umus
    -0.08
    æŃ»ä¸į
    -0.08
     almeno
    -0.07
    POSITIVE LOGITS
    å¾Īå°ij
    0.10
    å¾ĪçŁŃ
    0.10
    çŁŃçŁŃ
    0.09
    å°ijæķ°
    0.09
     wenigen
    0.09
     barely
    0.09
    寥寥
    0.09
    å¾Īå°ıçļĦ
    0.09
     wenige
    0.08
    ãģĹãģĭ
    0.08
    Activations Density 0.204%

    No Known Activations