© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30433
    Prev
    Next
    INDEX
    Explanations

    group composition or change

    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
    å®ĥä»¬åľ¨
    -0.08
     Elles
    -0.07
    ÏĦÏģ
    -0.07
    åľ¨æł¡æľŁéĹ´
    -0.07
    æ¯įæł¡
    -0.07
    ccb
    -0.07
     bạc
    -0.07
    å®ĥ们çļĦ
    -0.07
     ÑĢабоÑĤодаÑĤелÑı
    -0.07
    æł¡æĸ¹
    -0.07
    POSITIVE LOGITS
    人æķ°
    0.14
    çļĦ人æķ°
    0.13
    人æķ°çļĦ
    0.13
    人群
    0.12
    人æķ¸
    0.12
     roster
    0.12
    åIJįåįķ
    0.11
    ä»Ģä¹Ī人
    0.11
    ä»Ģä¹Īæł·çļĦ人
    0.11
    çļĦ人群
    0.11
    Activations Density 0.541%

    No Known Activations