© 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. 17420
    Prev
    Next
    INDEX
    Explanations

    anarchist, libertarian, poverty

    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
     polar
    -0.06
     Polar
    -0.06
    ẻ
    -0.06
    æ´
    -0.05
    æ´ĭ
    -0.05
    æ¼Ĥ
    -0.05
    ptes
    -0.05
    emed
    -0.05
    è¾ĥå·®
    -0.05
    én
    -0.05
    POSITIVE LOGITS
     économ
    0.06
    æĹłçĹķ
    0.06
    геÑĤи
    0.06
    undy
    0.05
    ustin
    0.05
    èĩ´çļĦ
    0.05
    è·¯åı£
    0.05
     comb
    0.05
    èIJ½åľ°
    0.05
     hiến
    0.05
    Activations Density 0.018%

    No Known Activations