© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30073
    Prev
    Next
    INDEX
    Explanations

    mathematical integrals and summation notation

    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
    eny
    -0.07
    oid
    -0.07
    -
    -0.07
    uo
    -0.07
    ye
    -0.06
    ieu
    -0.06
    ena
    -0.06
    年第
    -0.06
    endorf
    -0.06
    çĵ
    -0.06
    POSITIVE LOGITS
    -contrib
    0.09
    æѤ类
    0.08
    ä»Ģä¹Īåij¢
    0.08
    ниÑĤ
    0.08
    {*
    0.08
    PropTypes
    0.08
    Õ²
    0.07
    меÑģÑĤи
    0.07
    errat
    0.07
    isplay
    0.07
    Activations Density 0.007%

    No Known Activations