© 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. 20956
    Prev
    Next
    INDEX
    Explanations

    code comments and symbols

    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
    çĴ¨
    -0.07
    oved
    -0.07
    кÑĢа
    -0.06
    ochond
    -0.06
    ä¸įçķĻ
    -0.06
    utura
    -0.06
    åĴĮåIJİ
    -0.06
    åºĶå°Ĩ
    -0.06
    ç¼ļ
    -0.06
     Secund
    -0.06
    POSITIVE LOGITS
    é¥
    0.06
     quen
    0.05
    ä»»ä½ķå½¢å¼ıçļĦ
    0.05
     freely
    0.05
    çļĦä»»ä½ķ
    0.05
     timeless
    0.05
    arters
    0.05
     reap
    0.05
     torno
    0.05
     sanction
    0.05
    Activations Density 0.116%

    No Known Activations