© 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. 39096
    Prev
    Next
    INDEX
    Explanations

    parentheses and numbers

    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
    çªģåĩº
    -0.07
    éļı
    -0.07
    èħĨ
    -0.07
    .required
    -0.07
     oportun
    -0.06
    æĭĸ
    -0.06
    å¯IJ
    -0.06
    ä¼ļéļıçĿĢ
    -0.06
    éļıæŶ
    -0.06
    ä¸İ人
    -0.06
    POSITIVE LOGITS
     substitute
    0.08
    æĬķèµĦ建议
    0.07
    代åħ¥
    0.07
    ëł¹
    0.07
     Substitute
    0.07
    owo
    0.07
     GNU
    0.07
    æľºæ¢°å·¥ç¨ĭ
    0.07
    _MAGIC
    0.07
     Inputs
    0.07
    Activations Density 0.009%

    No Known Activations