© 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. 55999
    Prev
    Next
    INDEX
    Explanations

    citizen and citizenship

    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
    ç¨ĭ度ä¸Ĭ
    -0.09
    åĬ¿å¤´
    -0.09
    hle
    -0.09
    inator
    -0.08
    ño
    -0.08
    ehan
    -0.08
    æľĢä¸ĵä¸ļçļĦ
    -0.08
    yron
    -0.08
    ldata
    -0.08
    Leod
    -0.08
    POSITIVE LOGITS
    åħ¬æ°ij
    0.11
     citizenship
    0.10
     citizens
    0.08
     citizen
    0.08
     гÑĢажданина
    0.07
    izens
    0.07
    æ³ķ
    0.07
    åıĤä¸İæ´»åĬ¨
    0.07
     Citizenship
    0.06
    ande
    0.06
    Activations Density 0.022%

    No Known Activations