© 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. 45096
    Prev
    Next
    INDEX
    Explanations

    outer corner

    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
    ç¯Ŀ
    -0.09
    对å®ĥ
    -0.08
    ä¸İåħ¶
    -0.08
    .fe
    -0.08
    ä¸İèĩªå·±
    -0.08
    landet
    -0.08
    çĭ¬åѤ
    -0.08
    ibaldi
    -0.07
    ÏĢÎŃ
    -0.07
    æĭ¿åľ°
    -0.07
    POSITIVE LOGITS
    çļĦä¸Ģ对
    0.10
    两人çļĦ
    0.09
     exchanged
    0.09
    åıĮæĸ¹çļĦ
    0.09
    ä¸¤åĽ½
    0.08
    æĪijä¿©
    0.08
    åıĮæĸ¹åľ¨
    0.08
    ä¸¤åľ°
    0.08
    åıĮæĸ¹
    0.08
     differences
    0.08
    Activations Density 0.132%

    No Known Activations