© 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. 62431
    Prev
    Next
    INDEX
    Explanations

    citation markers like [@

    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
    mons
    -0.07
     ÙĪار
    -0.07
    chter
    -0.07
    ÐijÐŀ
    -0.07
    nis
    -0.06
    .intValue
    -0.06
    ä½łåĴĮ
    -0.06
    Talk
    -0.06
    é¢ĺåºĵ
    -0.06
    ι
    -0.06
    POSITIVE LOGITS
    ://
    0.08
    عث
    0.07
    _wrap
    0.07
    à¸Ĥว
    0.07
    à¹Īà¸ĩ
    0.07
    ãĥªãĥĥãĤ¯
    0.07
    زاز
    0.07
    _CHILD
    0.07
    ewood
    0.07
    iksa
    0.07
    Activations Density 0.053%

    No Known Activations