© 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. 20331
    Prev
    Next
    INDEX
    Explanations

    attached/attachment

    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
     over
    -0.07
    ä¸įä¸ĭ
    -0.07
     précis
    -0.07
    主导
    -0.07
    åĸľæĢĴ
    -0.06
    æĦ§
    -0.06
    emme
    -0.06
    enius
    -0.06
    æļĤè¡Į
    -0.06
    ³
    -0.06
    POSITIVE LOGITS
    åı¦ä¸Ģ端
    0.10
     attached
    0.09
    Ended
    0.09
    attachment
    0.09
    Attached
    0.09
     attachment
    0.09
    attached
    0.09
     Attached
    0.09
    Attachment
    0.08
    éĤ£è¾¹çļĦ
    0.08
    Activations Density 0.007%

    No Known Activations