© 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. 9147
    Prev
    Next
    INDEX
    Explanations

    next term in sequences

    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
     regia
    -0.07
    亡
    -0.07
    /connection
    -0.07
    etti
    -0.07
    泡水
    -0.07
    indir
    -0.06
    æĮĤäºĨ
    -0.06
     Uses
    -0.06
    omos
    -0.06
    epy
    -0.06
    POSITIVE LOGITS
    зиÑĤ
    0.08
    åĨįä¸Ģ次
    0.08
    تÙĩÙħ
    0.07
    ÑĨева
    0.07
    åĨį次
    0.07
    무를
    0.07
    æĥ³æĿ¥
    0.07
    Č↵
    0.07
    æľįåĬ¡å¹³åı°
    0.07
    éĻ¢çļĦ
    0.07
    Activations Density 0.022%

    No Known Activations