© 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. 47818
    Prev
    Next
    INDEX
    Explanations

    society or civilization

    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
    ами
    -0.10
    ाल
    -0.10
    manship
    -0.09
    кидÑĭ
    -0.09
    elson
    -0.09
    äºĨäºĭ
    -0.09
    yen
    -0.09
    stens
    -0.09
    ister
    -0.09
    orary
    -0.08
    POSITIVE LOGITS
    Ñı
    0.07
    -wide
    0.07
    wide
    0.06
    's
    0.06
    sein
    0.06
    ÑĤа
    0.06
    /language
    0.06
     civilization
    0.06
    de
    0.06
    -threatening
    0.06
    Activations Density 0.015%

    No Known Activations