© 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. 31968
    Prev
    Next
    INDEX
    Explanations

    quantities and units

    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
    tigt
    -0.09
    ç¼ĸè¾ijäºİ
    -0.08
     especialmente
    -0.07
    umni
    -0.07
    å°½åı¯èĥ½
    -0.07
    ÐĵÐIJ
    -0.07
    ieux
    -0.07
    为æĤ¨æݨèįIJ
    -0.07
    åĤ»åĤ»
    -0.07
     surtout
    -0.07
    POSITIVE LOGITS
    èĢĮåħ¶
    0.09
    ä¹ĭå¤ļ
    0.08
    å·¦åı³
    0.07
    ol
    0.06
    æīĢ带æĿ¥çļĦ
    0.06
    å½ĵåħ¶
    0.06
    æĺķ
    0.06
    oo
    0.06
    åIJĦç§įåIJĦæł·çļĦ
    0.06
    ä¹ĭåĨħ
    0.06
    Activations Density 0.348%

    No Known Activations