© 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. 38886
    Prev
    Next
    INDEX
    Explanations

    `uuid`

    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
    à®±à¯įà®±
    -0.08
    yses
    -0.08
    atsby
    -0.08
    .hw
    -0.07
    endon
    -0.07
    æ±
    -0.07
    veis
    -0.07
    rana
    -0.07
    å±ĪæĮĩ
    -0.07
    roman
    -0.07
    POSITIVE LOGITS
    æĿ¥èĩªç½ij绾
    0.08
    ç¥ŀåħµ
    0.07
     [/
    0.07
    æľīçĶ¨çļĦ
    0.06
    æľīäºĭ
    0.06
    æĪIJ份
    0.06
    ixe
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    ä¸Ģ个个
    0.06
    åѦä¼ļ
    0.06
    Activations Density 0.002%

    No Known Activations