© 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. 58317
    Prev
    Next
    INDEX
    Explanations

    asymptotics 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
    ìĩĦ
    -0.07
    untr
    -0.06
    ụng
    -0.06
    ä¸įæĸ¹ä¾¿
    -0.06
    æķĪåĬĽçļĦ
    -0.06
    梵
    -0.06
    èĩªçĶ±
    -0.06
    é±¼
    -0.06
    ãģijãģªãģĦ
    -0.06
    obil
    -0.06
    POSITIVE LOGITS
    ratio
    0.09
    çļĦå¹³åĿĩ
    0.09
     ratio
    0.08
    ä¸ĢæĪIJ
    0.08
     average
    0.08
    Ratio
    0.08
     Moy
    0.08
    average
    0.08
    _ratio
    0.08
    Avg
    0.08
    Activations Density 0.009%

    No Known Activations