© 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. 63935
    Prev
    Next
    INDEX
    Explanations

    code syntax and programming languages

    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
    ä¹ĥ
    -0.08
    ingg
    -0.08
    å·¥åѦéĻ¢
    -0.08
    ä¸įåĢ¦
    -0.07
     theoretically
    -0.07
    <tag
    -0.07
     Roya
    -0.07
    ãĤ³ãĥ©ãĥł
    -0.07
    VT
    -0.07
    isseur
    -0.07
    POSITIVE LOGITS
     expressions
    0.07
     expression
    0.07
    fen
    0.07
    表达
    0.07
     «
    0.07
    ahir
    0.07
    ä¾Ŀ次
    0.07
     íijľíĺĦ
    0.07
     Everything
    0.07
    ald
    0.07
    Activations Density 0.010%

    No Known Activations