© 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. 31633
    Prev
    Next
    INDEX
    Explanations

    questions about variables

    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
    analysis
    -0.06
    æīĢ以对äºİ
    -0.06
     analyses
    -0.06
    ä¸İæĮijæĪĺ
    -0.06
    æĶ¹åıĺ
    -0.06
    utang
    -0.06
    жал
    -0.06
    åĴĮèĥ½åĬĽ
    -0.06
    并ä¸į代表
    -0.05
    _prepare
    -0.05
    POSITIVE LOGITS
    åĢ¼æĺ¯
    0.08
    bach
    0.08
    reif
    0.07
    Ủ
    0.07
    åľ¨çº¿éĺħ读
    0.07
    æ¼ĶçļĦ
    0.07
    αÏĤ
    0.07
    ÑģлÑĥ
    0.07
     isize
    0.07
    æĻ®æŀĹ
    0.07
    Activations Density 0.026%

    No Known Activations