© 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. 28983
    Prev
    Next
    INDEX
    Explanations

    cities and locations

    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
    emed
    -0.07
    以ä¸ĭåĩłç§į
    -0.07
    å¼Ĭ
    -0.07
    =all
    -0.06
    _sa
    -0.06
    å±±æĻ¯åĮº
    -0.06
     Zas
    -0.06
    qs
    -0.06
     ==(
    -0.06
     bid
    -0.06
    POSITIVE LOGITS
    ois
    0.07
    [array
    0.07
    é¡»åľ¨
    0.07
    éĺħè¯»æľ¬æĸĩ
    0.07
    zinho
    0.07
    culate
    0.07
    esson
    0.07
     Vel
    0.07
    å°Ķ夫
    0.06
    VEL
    0.06
    Activations Density 0.190%

    No Known Activations