© 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. 24388
    Prev
    Next
    INDEX
    Explanations

    level of liquid

    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
    å¾ĹæĦı
    -0.07
    ç¨İ
    -0.07
    å°ıåĪ°
    -0.06
     kus
    -0.06
    kus
    -0.06
    PathParam
    -0.06
     Robbins
    -0.06
    å®īæİĴ
    -0.06
    æľĢ大åĬŁçİĩ
    -0.06
     struct
    -0.06
    POSITIVE LOGITS
     vạch
    0.09
    æłĩ线
    0.09
    ä½įç½®
    0.09
    казаниÑı
    0.09
    ä½įç½®çļĦ
    0.09
     markings
    0.08
    CIL
    0.08
    ä½įç½®åĴĮ
    0.08
    读æķ°
    0.08
    ÑĢовенÑĮ
    0.08
    Activations Density 0.006%

    No Known Activations