© 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. 51269
    Prev
    Next
    INDEX
    Explanations

    .h file extensions

    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
    æµģè¿ŀ
    -0.08
    celli
    -0.08
    æľºä½ĵ
    -0.06
    åħ¨æľ¬å°ı说
    -0.06
    ipo
    -0.06
    itera
    -0.06
    .DE
    -0.06
     waarmee
    -0.06
    athe
    -0.06
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.06
    POSITIVE LOGITS
    wati
    0.07
    ikal
    0.07
    åIJįåī¯
    0.07
    大åĬĽå®ŀæĸ½
    0.07
    åľ¨æĸ°çļĦä¸Ģå¹´éĩĮ
    0.07
    ayos
    0.07
    ---
    0.07
     Codec
    0.06
    Ù°
    0.06
    ouse
    0.06
    Activations Density 0.007%

    No Known Activations