© 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. 17565
    Prev
    Next
    INDEX
    Explanations

    cloud/AWS/CDN/URLs

    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
    uml
    -0.07
    å°Ķå¾·
    -0.07
    neau
    -0.07
    è¯ļèģĺèĭ±æīį
    -0.07
    olling
    -0.07
    çĽ¸å®¹
    -0.07
    å¦Ĥæ½®
    -0.07
    æŁ¥çľĭåħ¨æĸĩ
    -0.07
    _strerror
    -0.07
    解éļ¾
    -0.07
    POSITIVE LOGITS
    ä¸į说è¯Ŀ
    0.07
     Rad
    0.07
    вли
    0.06
    \a
    0.06
    ÑĩаÑģ
    0.06
    諸
    0.06
     {}).
    0.06
    Rad
    0.06
    æij
    0.06
    quis
    0.06
    Activations Density 0.018%

    No Known Activations