© 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. 19648
    Prev
    Next
    INDEX
    Explanations

    of the

    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
    bergen
    -0.07
    ).__
    -0.07
    ä¸ĢäºĽéĹ®é¢ĺ
    -0.07
    าà¸Ļิ
    -0.07
    mans
    -0.06
    _("
    -0.06
    åĮĹæµ·
    -0.06
    »
    -0.06
    ãģ¿ãģª
    -0.06
    INCI
    -0.06
    POSITIVE LOGITS
    æķ´ä¸ª
    0.09
    æķ´ä¸ªäºº
    0.08
     gesamten
    0.08
     entire
    0.08
     ANY
    0.08
    ä»»ä½ķå½¢å¼ıçļĦ
    0.07
     вообÑīе
    0.07
    ä»»ä½ķåħ¶ä»ĸ
    0.07
    æķ´ä¸ªéĹ®é¢ĺ
    0.07
     конкÑĢеÑĤно
    0.07
    Activations Density 0.216%

    No Known Activations