© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 55342
    Prev
    Next
    INDEX
    Explanations

    code syntax delimiters

    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
    欢声
    -0.08
    oreign
    -0.08
    XHR
    -0.08
    åĩłæŃ¥
    -0.08
    家éķ¿ä¼ļ
    -0.07
    маÑı
    -0.07
    çī©åĴĮ
    -0.07
    人æĹł
    -0.07
     inad
    -0.07
     hÃło
    -0.07
    POSITIVE LOGITS
    ensi
    0.07
     Gregg
    0.07
    漫
    0.07
    éĻIJåĪ¶
    0.07
    éĻIJ
    0.06
     assumed
    0.06
     predefined
    0.06
    éĩijåħī
    0.06
     modeled
    0.06
    ers
    0.06
    Activations Density 0.009%

    No Known Activations