© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20533
    Prev
    Next
    INDEX
    Explanations

    land owner/resident

    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
    éĢļåĪĻ
    -0.06
    Rép
    -0.06
    GUN
    -0.06
    held
    -0.06
    ноÑģÑĤÑĢан
    -0.06
    avn
    -0.06
    keep
    -0.06
    gratis
    -0.06
    ä¿ĿæĮģåľ¨
    -0.06
    æĸ°åĬłåĿ¡
    -0.05
    POSITIVE LOGITS
    unya
    0.05
    itty
    0.05
    æľīæĦŁ
    0.05
    ä¸įçł´
    0.05
    Ø«Ùħ
    0.05
    æ»ĭ
    0.05
    å¤ķ
    0.05
    orr
    0.05
    åĥıä¸Ģåıª
    0.05
    ![
    0.05
    Activations Density 0.062%

    No Known Activations