© 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. 8762
    Prev
    Next
    INDEX
    Explanations

    asymptotic behavior and limits

    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
    egis
    -0.10
    é½IJåħ¨çļĦ
    -0.08
     duplic
    -0.07
    é½IJåħ¨
    -0.07
    .Constraint
    -0.07
     intr
    -0.07
    ãĥŁãĤ¹
    -0.07
    çļĦä¿ĿæĬ¤
    -0.07
    éten
    -0.07
     retal
    -0.07
    POSITIVE LOGITS
     asympt
    0.11
    æ¸IJè¿Ľ
    0.11
    æ¸IJ
    0.10
    lim
    0.10
     convergence
    0.10
     tiá»ĩm
    0.09
    è¶ĭåĬ¿
    0.09
    漸
    0.09
    æĶ¶æķĽ
    0.08
     gradual
    0.08
    Activations Density 0.028%

    No Known Activations