© 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. 8150
    Prev
    Next
    INDEX
    Explanations

    four groups, combinations, classifications, configurations

    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
    æķ´
    -0.08
    _MACHINE
    -0.06
    uesta
    -0.06
     \"{
    -0.06
    ube
    -0.06
     \"$
    -0.06
    第ä¸Ģ天
    -0.06
    cule
    -0.06
    æķ´æľº
    -0.06
    pent
    -0.06
    POSITIVE LOGITS
     quadrant
    0.10
    idet
    0.08
    åĽĽæĸ¹
    0.08
    zzle
    0.08
    ربع
    0.07
    ezu
    0.07
    ENU
    0.07
    鸳鸯
    0.07
    è§ĴèIJ½
    0.07
     ÑĩеÑĤвеÑĢ
    0.07
    Activations Density 0.034%

    No Known Activations