© 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. 11675
    Prev
    Next
    INDEX
    Explanations

    equations 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
    creator
    -0.08
    汽车éħį件
    -0.08
    ngine
    -0.07
    ãģĻãģ¿
    -0.07
    .Registry
    -0.07
    каÑĤ
    -0.07
    ovor
    -0.07
     számÃŃt
    -0.07
    æĶ¯ä»ĺçļĦ
    -0.07
    ricia
    -0.07
    POSITIVE LOGITS
    Equality
    0.11
     equation
    0.11
     Rear
    0.10
    æĸ¹ç¨ĭ
    0.10
     equality
    0.10
     Equality
    0.10
    æĸ¹ç¨ĭå¼ı
    0.10
     rearr
    0.10
     equations
    0.09
     Equation
    0.09
    Activations Density 0.007%

    No Known Activations