© 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. 64438
    Prev
    Next
    INDEX
    Explanations

    rainfall, populations, percent

    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
    kens
    -0.10
    .contents
    -0.08
    éķ¿æľŁä½¿çĶ¨
    -0.08
    å¸Ĥå§Ķç»Ħç»ĩéĥ¨
    -0.08
    æĮĸæİĺåħ¬åı¸
    -0.07
    ê±°
    -0.07
    ä¾ĽåºĶä¿¡æģ¯
    -0.07
     Ecke
    -0.07
    å¸Ĥè´¢æĶ¿å±Ģ
    -0.07
    è¡¡éĺ³
    -0.07
    POSITIVE LOGITS
    åIJĮæ¯Ķ
    0.08
    å¢ŀéķ¿äºĨ
    0.08
     trend
    0.07
    表ä¸Ń
    0.07
    åħ¨å¹´
    0.07
    åĽ¾ä¸Ĭ
    0.07
    åIJĮæ¯Ķå¢ŀéķ¿
    0.07
    该项
    0.07
    æ¯Ķä¸Ĭå¹´
    0.07
    çݯæ¯Ķ
    0.07
    Activations Density 0.005%

    No Known Activations