© 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. 47947
    Prev
    Next
    INDEX
    Explanations

    liquid crystal

    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
    -panel
    -0.08
    å¯¹æľ¬æ¬¡
    -0.08
     retrospective
    -0.08
    .panel
    -0.08
    ÑģпоÑĢ
    -0.07
    panel
    -0.07
    åIJĦè·¯
    -0.07
    .repo
    -0.07
    延年
    -0.07
     panels
    -0.07
    POSITIVE LOGITS
    容åĻ¨
    0.09
    åĽºä½ĵ
    0.08
    ç²ĴåŃIJ
    0.08
    稳
    0.08
    å¯Ĩ度
    0.08
     cohesion
    0.07
     compression
    0.07
    æµģåĬ¨
    0.07
    åİĭ缩
    0.07
     pudd
    0.07
    Activations Density 0.001%

    No Known Activations