© 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. 62742
    Prev
    Next
    INDEX
    Explanations

    code punctuation

    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
    иÑİ
    -0.07
    ersh
    -0.07
     plus
    -0.07
    åij¨å²ģçļĦ
    -0.07
    andy
    -0.06
    cim
    -0.06
    hdr
    -0.06
    iken
    -0.06
    oren
    -0.06
    ante
    -0.06
    POSITIVE LOGITS
    ypes
    0.07
    áĢ¸
    0.07
    cope
    0.07
    bsites
    0.07
    æĸ¹æĸ¹éĿ¢
    0.07
    ä»Ģä¹Īåij¢
    0.07
    ustria
    0.07
    à¸Ļà¹Į
    0.07
     underrated
    0.07
    dden
    0.07
    Activations Density 0.059%

    No Known Activations