© 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. 16668
    Prev
    Next
    INDEX
    Explanations

    national park 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
    anness
    -0.07
    tent
    -0.07
    DESC
    -0.07
    å¸Īé£İ
    -0.07
     gross
    -0.07
    ci
    -0.06
    ä¸įæĹ©
    -0.06
    ANGAN
    -0.06
     distr
    -0.06
    nios
    -0.06
    POSITIVE LOGITS
    å·²ç»ıè¿Ľåħ¥
    0.07
    poste
    0.07
    ¿
    0.07
    krim
    0.07
    zne
    0.07
    ogn
    0.07
    charges
    0.07
    unst
    0.06
    %^
    0.06
     tatt
    0.06
    Activations Density 0.004%

    No Known Activations