© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 20414
    Prev
    Next
    INDEX
    Explanations

    code constructs

    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
    itr
    -0.09
    æĭīéĩĮ
    -0.07
    .promise
    -0.07
    é¹ĥ
    -0.07
    åĴĮ马
    -0.07
    éªı
    -0.07
    inton
    -0.07
    鼰
    -0.07
    atson
    -0.07
    оеди
    -0.07
    POSITIVE LOGITS
    PLIC
    0.07
    -automatic
    0.07
    å®ŀè´¨æĢ§
    0.07
    äng
    0.07
    ament
    0.07
    ार
    0.06
    parsers
    0.06
    categ
    0.06
    panic
    0.06
    ড়
    0.06
    Activations Density 0.053%

    No Known Activations