© 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. 17358
    Prev
    Next
    INDEX
    Explanations

    commands, SQL Server, update, retrieve, Leymus, compare, WHO, average, pre-fill

    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
     thôi
    -0.06
    çļĦéĤ£ä¸ª
    -0.05
    ä¸ŃçļĦä¸Ģ个
    -0.05
    ido
    -0.05
    conte
    -0.05
     implementation
    -0.05
     Sail
    -0.05
    jsonwebtoken
    -0.05
     dáng
    -0.04
    -/
    -0.04
    POSITIVE LOGITS
    ussian
    0.07
    antic
    0.06
    phans
    0.06
    uban
    0.06
    Ú©Ûģ
    0.06
     Ire
    0.05
    umat
    0.05
     passive
    0.05
    trecht
    0.05
    fique
    0.05
    Activations Density 0.055%

    No Known Activations