© 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. 33108
    Prev
    Next
    INDEX
    Explanations

    file paths or filenames

    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
    rup
    -0.08
    ئة
    -0.07
    ucc
    -0.07
    ruc
    -0.07
    abut
    -0.07
    nolog
    -0.07
    vik
    -0.07
    ÅŁik
    -0.07
    ases
    -0.07
    ÑĨи
    -0.07
    POSITIVE LOGITS
    stdarg
    0.07
    æĪijåĴĮæĪijçļĦ
    0.07
    æ²¹çĥŁæľº
    0.07
    ablo
    0.06
    å¾Ĺ主
    0.06
     reopen
    0.06
     =================================================================================
    0.06
     Editions
    0.06
    两å¥Ĺ
    0.06
    Splash
    0.06
    Activations Density 0.002%

    No Known Activations