© 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. 24080
    Prev
    Next
    INDEX
    Explanations

    proper nouns or specific entities

    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
    ä»ħä»£è¡¨ä½ľèĢħæľ¬äºº
    -0.10
     Ilmais
    -0.08
    oret
    -0.08
    æľ¨é½IJ
    -0.07
    بتÙĩا
    -0.07
    尼迪
    -0.07
    inois
    -0.07
    ä¸įä¼ļæĺ¯
    -0.07
    ำ
    -0.07
    кладки
    -0.07
    POSITIVE LOGITS
     has
    0.08
     itself
    0.08
    éĻ¤äºĨæľī
    0.08
    æľ¬èº«
    0.07
     boasts
    0.07
    æīįæĺ¯
    0.06
    åĩłä¹İæīĢæľī
    0.06
    achu
    0.06
    æľ¬èº«çļĦ
    0.06
     also
    0.06
    Activations Density 0.031%

    No Known Activations