© 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. 47729
    Prev
    Next
    INDEX
    Explanations

    equation or math formulation

    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
    羿
    -0.07
    elic
    -0.07
    kena
    -0.07
    DRV
    -0.07
    edBy
    -0.07
    ĵ
    -0.07
    abee
    -0.07
    iligen
    -0.06
     numb
    -0.06
    _EXIT
    -0.06
    POSITIVE LOGITS
     equations
    0.11
     equation
    0.10
    æĸ¹ç¨ĭ
    0.09
     governing
    0.09
     Equation
    0.08
    æĸ¹ç¨ĭå¼ı
    0.08
    æļĤè¡Į
    0.08
     eq
    0.07
    iform
    0.07
    riture
    0.07
    Activations Density 0.010%

    No Known Activations