© 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. 29685
    Prev
    Next
    INDEX
    Explanations

    concurrent edits or actions

    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
    gil
    -0.07
    å¤ĸæĮĤ
    -0.07
    ASON
    -0.07
    باÙĦ
    -0.06
    代代
    -0.06
    åIJij社ä¼ļ
    -0.06
    åļİ
    -0.06
    moni
    -0.06
    ÑĢк
    -0.06
    ä¾ĽåĽ¾
    -0.06
    POSITIVE LOGITS
     subsequently
    0.10
     subsequent
    0.10
    éļıåIJİ
    0.10
    éļıåIJİçļĦ
    0.09
     بعدÙĩا
    0.08
    igner
    0.08
     بعدÙĩ
    0.08
    åIJİç»Ń
    0.08
    ç´§æİ¥çĿĢ
    0.08
    åĨįä¹Łæ²¡æľī
    0.08
    Activations Density 0.120%

    No Known Activations