© 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. 47021
    Prev
    Next
    INDEX
    Explanations

    closing parentheses or semicolons

    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
    orar
    -0.07
    éĹªçĥģçĿĢ
    -0.07
    éĢłçī©
    -0.06
    ared
    -0.06
    undy
    -0.06
    زÙĨد
    -0.06
    anu
    -0.06
     gur
    -0.06
    å¼ĤæĢ§
    -0.06
    羿
    -0.06
    POSITIVE LOGITS
     print
    0.08
    edReader
    0.07
    åħ¶èº«
    0.07
    print
    0.07
    ţ
    0.07
    æīĵåį°
    0.06
    ä¹ĭ为
    0.06
    ÑģÑĮ
    0.06
    osaur
    0.06
     Tracker
    0.06
    Activations Density 0.014%

    No Known Activations