© 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. 44010
    Prev
    Next
    INDEX
    Explanations

    Show HN; quora.com

    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
    家天ä¸ĭ
    -0.07
    ÙĦات
    -0.07
    æīĺ
    -0.07
    ìĬ¹
    -0.06
    æī«çłģåħ³æ³¨
    -0.06
     Comet
    -0.06
    ষ
    -0.06
     Exc
    -0.06
    è¨Ĺ
    -0.06
    å®Ŀå±±
    -0.06
    POSITIVE LOGITS
    OperationException
    0.08
    èĢ
    0.07
    orida
    0.07
     мол
    0.07
    ÑģÑĤÑĢе
    0.07
    towe
    0.07
    å¥
    0.06
    并请
    0.06
     Moreira
    0.06
    ãĥ«ãĤ¯
    0.06
    Activations Density 0.015%

    No Known Activations