© 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. 40627
    Prev
    Next
    INDEX
    Explanations

    times, content, short, distinct, limit, protection, times, %, complexity, rankings

    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
    æľĢæĸ°è¯Ħ论
    -0.07
    ÑĦоÑĢ
    -0.07
    reh
    -0.07
    éĺ¿åħĭ
    -0.07
    ợt
    -0.07
    æ¸Ŀ
    -0.07
    ãĥ©ãĥ«
    -0.07
    _overlap
    -0.07
    óra
    -0.07
    inals
    -0.07
    POSITIVE LOGITS
    æĮĩçļĦæĺ¯
    0.12
    æĺ¯éĴĪ对
    0.11
     referring
    0.11
     refers
    0.10
    æĺ¯æĮĩ
    0.10
    主è¦ģæĺ¯æĮĩ
    0.10
    主è¦ģéĴĪ对
    0.09
    说çļĦæĺ¯
    0.09
    æĺ¯æĮĩåľ¨
    0.09
    ãģĤãģı
    0.09
    Activations Density 0.196%

    No Known Activations