© 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. 44924
    Prev
    Next
    INDEX
    Explanations

    defining name or sequence

    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
    pline
    -0.08
    ä¸Ģç¯ĩæĸĩç«ł
    -0.07
    èĭ¥å¹²éĹ®é¢ĺçļĦ
    -0.07
    agna
    -0.07
    aan
    -0.07
    iep
    -0.07
    barkeit
    -0.07
    ÑģмоÑĤÑĢи
    -0.07
     severely
    -0.07
    å¯¹ä½łè¯´
    -0.07
    POSITIVE LOGITS
    à¹Ĥà¸Ĺษ
    0.07
    æĿ¥èĩª
    0.07
    æĿ¥èĩªä¸ŃåĽ½
    0.07
    æĹ©æĺ¥
    0.06
    -makers
    0.06
     definitions
    0.06
     {?}
    0.06
    áĥĿáĥĵ
    0.06
    ลà¸ĩà¹Ħà¸Ľ
    0.06
     definition
    0.06
    Activations Density 0.009%

    No Known Activations