© 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. 58289
    Prev
    Next
    INDEX
    Explanations

    `function` or `method` calling `map` or `pop` or `ajax`

    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
    äºĨåIJ§
    -0.06
    èµ·æĿ¥äºĨ
    -0.06
    å¾Īå¤ļä¸ľè¥¿
    -0.06
    å¹¿åľºä¸Ĭ
    -0.06
    ä¹ĭ计
    -0.06
    n
    -0.06
    æĪĸæľī
    -0.06
    taj
    -0.06
    red
    -0.06
     fér
    -0.06
    POSITIVE LOGITS
    (_:
    0.08
    ,get
    0.08
     function
    0.08
    :function
    0.08
    stamp
    0.08
     Function
    0.07
    ,map
    0.07
    _trampoline
    0.07
    opsis
    0.07
    ,//
    0.07
    Activations Density 0.276%

    No Known Activations