© 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. 32176
    Prev
    Next
    INDEX
    Explanations

    state and province names

    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
     Mondiale
    -0.08
    _Global
    -0.08
    æīĢåľ¨åįķä½į
    -0.07
    ussen
    -0.07
     اÙĦعاÙĦÙħÙĬ
    -0.07
    usb
    -0.07
    opf
    -0.07
     mondiale
    -0.07
    үй
    -0.07
    opus
    -0.07
    POSITIVE LOGITS
    wide
    0.10
    /state
    0.09
    éĻħ
    0.09
    -wide
    0.08
    é¦ĸåºľ
    0.08
    åĴĮçľģ
    0.08
     пÑĢоживаниÑı
    0.08
    åľ¨åħ¨çľģ
    0.07
    举åįĹéĥ¨
    0.07
    åĮĹéĥ¨
    0.07
    Activations Density 0.174%

    No Known Activations