© 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. 60654
    Prev
    Next
    INDEX
    Explanations

    punctuation followed by programming terms

    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
    èįŁ
    -0.08
    /authentication
    -0.08
    sv
    -0.07
    å¤ĸæĸĩ
    -0.07
    shop
    -0.07
    ÙĪرا
    -0.07
    accio
    -0.07
    ãĤ¤ãĥ¤
    -0.07
    UMAN
    -0.07
    鲫
    -0.07
    POSITIVE LOGITS
    .Marshal
    0.07
    este
    0.07
    驻马
    0.07
    leger
    0.06
    wegen
    0.06
    æİ©
    0.06
    å¤ļåĸĿ
    0.06
    trate
    0.06
    antina
    0.06
     Marshal
    0.06
    Activations Density 0.351%

    No Known Activations