© 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. 12912
    Prev
    Next
    INDEX
    Explanations

    government and rulers

    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
    çIJĨäºĭéķ·
    -0.07
    иÑĤоÑĢ
    -0.07
    é¦Ĩéķ¿
    -0.07
    èĹ
    -0.07
    éķľå¤´
    -0.06
    Xã
    -0.06
     conjug
    -0.06
    æt
    -0.06
    à¥ĩत
    -0.06
    çIJĨäºĭ
    -0.06
    POSITIVE LOGITS
    areth
    0.08
    arra
    0.08
     authorities
    0.07
    oyer
    0.07
     administration
    0.07
     regime
    0.07
    JsonValue
    0.07
    -appointed
    0.07
     stability
    0.07
    atoi
    0.07
    Activations Density 0.179%

    No Known Activations