© 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. 7594
    Prev
    Next
    INDEX
    Explanations

    improve or increase something

    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
    ä½łçļĦ人
    -0.10
    ä½łèĩªå·±
    -0.10
    使人
    -0.09
    æĪij们èĩªå·±
    -0.08
     ourselves
    -0.08
     yourself
    -0.08
    ä½łæĥ³è¦ģçļĦ
    -0.08
    ä½łèĩªå·±çļĦ
    -0.08
    ä½ľèĢħæĺ¯
    -0.08
    人们对äºİ
    -0.08
    POSITIVE LOGITS
     ÑģвоиÑħ
    0.19
    使èĩªå·±çļĦ
    0.17
     Ñģвои
    0.16
    èĩªå·±çļĦ
    0.15
     Ñģвоей
    0.15
    åľ¨èĩªå·±çļĦ
    0.15
    å±ŀäºİèĩªå·±çļĦ
    0.15
     svých
    0.15
    åĴĮèĩªå·±çļĦ
    0.15
     Ñģвоем
    0.15
    Activations Density 1.511%

    No Known Activations