© 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. 49187
    Prev
    Next
    INDEX
    Explanations

    template, sheets, table, point, div, variable

    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
    engah
    -0.07
    obox
    -0.07
     Suri
    -0.06
    游æĪıä»ĭç»į
    -0.06
    gers
    -0.06
    oled
    -0.06
    ovin
    -0.06
    -même
    -0.06
    زÙħ
    -0.06
     Rage
    -0.06
    POSITIVE LOGITS
    ä¹ĭä¸ĢçļĦ
    0.11
    ات
    0.10
    们
    0.09
    éĹ´çļĦ
    0.09
    à¸ķà¹Īาà¸ĩà¹Ĩ
    0.09
    ä¹ĭéĹ´çļĦ
    0.09
    ä»¬åľ¨
    0.08
    ä¸ĢçļĦ
    0.08
    们对
    0.08
    “
    0.08
    Activations Density 0.004%

    No Known Activations