© 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. 38520
    Prev
    Next
    INDEX
    Explanations

    not by accident or chance

    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
    wik
    -0.07
    æľ¬æĿ¥
    -0.07
    calar
    -0.07
    ä¹Łå°±æĺ¯
    -0.07
    atab
    -0.06
    æĹ¢ä¸į
    -0.06
    æĪª
    -0.06
    ãģĤãģ¾ãĤĬ
    -0.06
    侧éĩįäºİ
    -0.06
    emed
    -0.06
    POSITIVE LOGITS
    è¿Ļä¹Īç®Ģåįķ
    0.10
    éĤ£ä¹Īç®Ģåįķ
    0.10
    èĢĮæĺ¯åľ¨
    0.10
    èĢĮæĺ¯ä¸Ģ个
    0.10
    ðŁĺĢ
    0.09
     nor
    0.09
    èĢĮæĺ¯åĽłä¸º
    0.09
    èĢĮæĺ¯
    0.09
    èĢĮæĺ¯è¦ģ
    0.08
     sondern
    0.08
    Activations Density 0.059%

    No Known Activations