© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17964
    Prev
    Next
    INDEX
    Explanations

    left and right wing politics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    大好
    -0.07
    ä¸Ģä½ĵçļĦ
    -0.06
    bey
    -0.06
    ç§ij大
    -0.06
    agem
    -0.06
    μά
    -0.06
    æĪijåı«
    -0.05
    velt
    -0.05
     ÙħÙĪج
    -0.05
    漩
    -0.05
    POSITIVE LOGITS
    ä¼ģä¸ļ
    0.06
    immen
    0.05
    à¸Ńà¸Ļ
    0.05
    ilib
    0.05
    ä½įç½®
    0.05
    eral
    0.05
     einsch
    0.05
    ellen
    0.05
    å®īåħ¨
    0.05
    ãģ»ãģ©
    0.05
    Activations Density 0.017%

    No Known Activations