© 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. 17013
    Prev
    Next
    INDEX
    Explanations

    is/are followed by conditions or qualifications

    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
    ä¸ĭåIJĮ
    -0.07
    elter
    -0.07
    ÑĢоÑģло
    -0.06
     zg
    -0.06
    åĽŀæѸ
    -0.06
     haline
    -0.06
    Õ¡Õ¿
    -0.06
    à¸Ńà¸Ļ
    -0.06
    ä¸ĢçŃ¹
    -0.06
     ÙħتÙħ
    -0.06
    POSITIVE LOGITS
    ä¸Ń央
    0.06
     central
    0.06
    ä»»æĦı
    0.06
     “
    0.06
     Central
    0.06
    Âł
    0.05
    âĢ¦
    0.05
     any
    0.05
     actual
    0.05
    Central
    0.05
    Activations Density 0.013%

    No Known Activations