© 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. 64198
    Prev
    Next
    INDEX
    Explanations

    telling or stating something

    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
    ampp
    -0.10
    åħ·ä½ĵæĿ¥è¯´
    -0.08
    opies
    -0.07
    celand
    -0.07
    ÙĨÛĮÙĨ
    -0.07
    tring
    -0.07
    mens
    -0.07
    hini
    -0.07
    ongyang
    -0.07
     Kushner
    -0.07
    POSITIVE LOGITS
    íĻĺ
    0.06
    çľĭä¸Ģä¸ĭ
    0.06
    EDA
    0.06
    èĩªå·±çļĦæĥ³æ³ķ
    0.06
    ött
    0.06
     spad
    0.06
    缮çļĦæĺ¯
    0.06
    lod
    0.06
    ãĢĮ
    0.06
     '
    0.06
    Activations Density 0.031%

    No Known Activations