© 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. 26784
    Prev
    Next
    INDEX
    Explanations

    announcements and news

    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
    åħĭæĸ¯
    -0.08
    å°½èģĮ尽责
    -0.07
    æ°ĵ
    -0.07
    lia
    -0.07
    illis
    -0.07
    hak
    -0.07
     Essays
    -0.06
    ç«Ńè¯ļ
    -0.06
    _responses
    -0.06
     Sido
    -0.06
    POSITIVE LOGITS
    à¸ļาà¸ĩà¸Ńยà¹Īาà¸ĩ
    0.12
     undisclosed
    0.11
    omething
    0.10
     concernant
    0.09
     something
    0.09
     concerning
    0.09
     Something
    0.09
     involving
    0.08
     berkaitan
    0.08
     regarding
    0.08
    Activations Density 0.442%

    No Known Activations