© 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. 8594
    Prev
    Next
    INDEX
    Explanations

    math formulas and inequalities

    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
    رة
    -0.08
    ÏĪη
    -0.07
    hing
    -0.07
    egna
    -0.07
    ثة
    -0.07
     podium
    -0.07
    вок
    -0.07
     punched
    -0.07
    å¨Ĩ
    -0.07
     ì¡´
    -0.07
    POSITIVE LOGITS
     bounding
    0.08
    漫
    0.08
    ä¼°ç®Ĺ
    0.08
    ä¸įæ¯Ķ
    0.08
     bounds
    0.08
    Bounding
    0.08
    bounds
    0.07
     Bounds
    0.07
    /we
    0.07
    ä¸įçŃī
    0.07
    Activations Density 0.013%

    No Known Activations