© 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. 3632
    Prev
    Next
    INDEX
    Explanations

    Maybe not or maybe something else

    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
    ively
    -0.13
    mere
    -0.10
    ses
    -0.10
    ات
    -0.10
    nyder
    -0.09
    uant
    -0.09
    عادة
    -0.09
    å¾Ģ常ä¸Ģæł·
    -0.09
    sie
    -0.09
    s
    -0.08
    POSITIVE LOGITS
    ting
    0.11
     saja
    0.11
     mắn
    0.09
    ÑĤеÑģÑĮ
    0.09
    人
    0.09
    theless
    0.09
    ÑĤÑİ
    0.08
    ëį°
    0.08
    ção
    0.08
    ÙĬÙĨ
    0.08
    Activations Density 0.019%

    No Known Activations