© 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. 43578
    Prev
    Next
    INDEX
    Explanations

    democracy and democratic contexts

    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
    INGS
    -0.11
    <|box_end|>
    -0.09
    ائع
    -0.08
    รุ
    -0.08
    ATIONS
    -0.08
     Mestre
    -0.08
    anea
    -0.08
    åij¨ä¸Ģèĩ³
    -0.08
    ELTS
    -0.08
    ings
    -0.08
    POSITIVE LOGITS
    -leaning
    0.09
    éĢī举
    0.08
    -minded
    0.08
     minded
    0.08
    -dem
    0.08
     democracy
    0.07
    åħ¬æ°ij
    0.07
    راء
    0.07
    dem
    0.07
    è¿Ľç¨ĭ
    0.07
    Activations Density 0.019%

    No Known Activations