© 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. 48142
    Prev
    Next
    INDEX
    Explanations

    levels and positions

    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
    è¡Įä¹ĭæľīæķĪçļĦ
    -0.07
    è§Ĩç½ij
    -0.07
    åĬ¨è¾Ħ
    -0.07
    éĽĨä¸ŃçļĦ
    -0.07
    æĹĹä¸ĭçļĦ
    -0.07
    iné
    -0.07
    缴æİ¥æĪĸ
    -0.06
    ÑĩнÑĭми
    -0.06
    çĤ¹æѤ
    -0.06
    áže
    -0.06
    POSITIVE LOGITS
    ä¹Łæĺ¯æ¯Ķè¾ĥ
    0.09
    åı¦ä¸Ģ个
    0.08
    ä»ħ次äºİ
    0.07
    ä¹Łæĺ¯æĪij们
    0.07
    第ä¸Ģ个
    0.07
    uter
    0.07
    æ¯Ķè¾ĥå°ı
    0.07
     najbolj
    0.07
    ndon
    0.06
    çijľ
    0.06
    Activations Density 0.024%

    No Known Activations