© 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. 22636
    Prev
    Next
    INDEX
    Explanations

    specific deficits or margins

    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
    åĵģè´¨åĴĮ
    -0.09
    ommer
    -0.08
    åĵģè´¨çļĦ
    -0.08
    ä»·æł¼åIJĪçIJĨ
    -0.08
    åĵģè´¨
    -0.08
    çļĦåĥ¹æł¼
    -0.07
    Editors
    -0.07
    isable
    -0.07
    æ¡ĤåĨł
    -0.07
     Mercer
    -0.07
    POSITIVE LOGITS
    èµ·çĤ¹
    0.09
     cumulative
    0.08
    累计
    0.07
    çŁŃæļĤ
    0.07
    ç´¯
    0.07
     never
    0.07
    éĢıæĶ¯
    0.07
     deficit
    0.07
     Peña
    0.06
    æļĤæŶçļĦ
    0.06
    Activations Density 0.003%

    No Known Activations