© 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. 22797
    Prev
    Next
    INDEX
    Explanations

    parts of URLs, dates, and comments

    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
    ä¸įå¾ĹäºĨ
    -0.07
    ست
    -0.07
    essel
    -0.07
    _PADDING
    -0.06
     Dangerous
    -0.06
    رÛĮ
    -0.06
     det
    -0.06
    ¶
    -0.06
     br
    -0.06
    igner
    -0.06
    POSITIVE LOGITS
    adget
    0.08
    meg
    0.08
    tober
    0.08
    andom
    0.07
    _separator
    0.07
    æ©ĺ
    0.07
    isco
    0.07
    åģĩæĹ¥
    0.07
    omid
    0.07
    elay
    0.07
    Activations Density 0.012%

    No Known Activations