© 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. 15222
    Prev
    Next
    INDEX
    Explanations

    quark, top quark

    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
    पà¥Ĥरà¥įण
    -0.08
    acons
    -0.08
    aute
    -0.08
    stead
    -0.08
    anee
    -0.08
    èĹ»
    -0.08
    edt
    -0.07
    acon
    -0.07
    -worthy
    -0.07
    é¡Į
    -0.07
    POSITIVE LOGITS
    /ne
    0.08
    ¢
    0.07
     pair
    0.07
    们çļĦ
    0.07
    åıĬåħ¶
    0.07
    纲
    0.07
    ä»¬åľ¨
    0.07
    /
    0.07
    /\
    0.06
    innen
    0.06
    Activations Density 0.002%

    No Known Activations