© 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. 47093
    Prev
    Next
    INDEX
    Explanations

    Porsche enthusiasts

    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
    æľīéĻIJ责任
    -0.06
     lic
    -0.06
     bore
    -0.05
    âĸ¡
    -0.05
    icaid
    -0.05
    epad
    -0.05
    èµĭ
    -0.05
    âĪ
    -0.05
     micro
    -0.05
    ifiable
    -0.05
    POSITIVE LOGITS
    ube
    0.09
    sache
    0.08
    驹
    0.08
     beho
    0.08
    ake
    0.08
    zsche
    0.08
    akes
    0.08
    人æĿ¥è¯´
    0.08
    _simps
    0.08
    veau
    0.08
    Activations Density 0.313%

    No Known Activations