© 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. 41214
    Prev
    Next
    INDEX
    Explanations

    search, scan, cache, algorithm

    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
    azon
    -0.07
     дам
    -0.07
    åħļç»Ħ
    -0.07
    ikko
    -0.07
    ä¸įå¿į
    -0.06
    _ER
    -0.06
    尼奥
    -0.06
    åľºåĿĩ
    -0.06
    chon
    -0.06
    usah
    -0.06
    POSITIVE LOGITS
     Algorithm
    0.09
    ç®Ĺæ³ķ
    0.08
     algorithm
    0.08
    Algorithm
    0.07
     Algo
    0.07
     process
    0.07
    æ³ķåĴĮ
    0.07
    ica
    0.07
    示ä¾ĭ
    0.07
    onz
    0.07
    Activations Density 0.015%

    No Known Activations