© 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. 46156
    Prev
    Next
    INDEX
    Explanations

    of the form $ / : [ f $

    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
    /@
    -0.08
    idel
    -0.07
    oop
    -0.07
     lẽ
    -0.07
    èµĦ产éĩįç»Ħ
    -0.07
    ä½ľä¸ºä¸Ģ项
    -0.07
    iore
    -0.07
    lÃŃ
    -0.07
    aed
    -0.07
    lime
    -0.07
    POSITIVE LOGITS
    :
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸Ļ
    0.08
    “
    0.08
    à¹Ģà¸Ķียวà¸ģัà¸ļ
    0.08
    ï¼ļ
    0.07
    ignment
    0.06
    ienia
    0.06
    æŁIJç§į
    0.06
    æīĢ示
    0.06
    ìĭĿìĿĦ
    0.06
    Activations Density 0.030%

    No Known Activations