© 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. 48008
    Prev
    Next
    INDEX
    Explanations

    information, intellect, or beneficial outcomes

    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
    è¿Ŀæ³ķåĴĮä¸įèī¯
    -0.09
    ampp
    -0.09
    ÃĩA
    -0.09
    alak
    -0.08
    éĻĪå°ı
    -0.08
    chio
    -0.08
    /device
    -0.08
    _HEAD
    -0.08
    åIJijæĹ¥
    -0.08
    паÑĢÑĤа
    -0.08
    POSITIVE LOGITS
     инÑĦоÑĢмаÑĨион
    0.08
     intellectually
    0.08
     intelect
    0.07
    omy
    0.07
    info
    0.07
    æ±ĤçŁ¥
    0.07
    çĽĺ
    0.06
     intellectual
    0.06
     uncover
    0.06
    æĶĢ
    0.06
    Activations Density 1.001%

    No Known Activations