© 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. 42553
    Prev
    Next
    INDEX
    Explanations

    sequence of variables $a_1, a_2, \dots, a_n$

    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
    ç«¥åŃIJ
    -0.06
    âĨĴ
    -0.06
    inus
    -0.06
    ä¸ĭ乡
    -0.06
    &
    -0.06
    ohn
    -0.06
    ↵
    -0.06
    ,
    -0.06
    eka
    -0.05
     ÙħÙĨÙĩÙħا
    -0.05
    POSITIVE LOGITS
    azos
    0.07
    kson
    0.07
    ëħĦê¹Įì§Ģ
    0.07
    lise
    0.07
    ä¸įæķĮ
    0.07
    yna
    0.07
    mén
    0.07
    fél
    0.07
    flater
    0.07
    大åı¯
    0.07
    Activations Density 0.009%

    No Known Activations