© 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. 21430
    Prev
    Next
    INDEX
    Explanations

    job opportunities and games

    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
     dep
    -0.06
     fo
    -0.05
    éter
    -0.05
    arahan
    -0.05
     groundwork
    -0.05
     fur
    -0.05
    گاÙĩ
    -0.05
     heights
    -0.05
     interval
    -0.05
    abil
    -0.05
    POSITIVE LOGITS
     ÐŁÐ¾ÑĢÑıд
    0.06
     ÐŁÑĢоÑĨедÑĥ
    0.06
     обÑĢе
    0.06
     frumo
    0.06
    æ¾
    0.06
    ä¸įæ¼ı
    0.05
     Thừa
    0.05
    รà¸Ńà¸ļ
    0.05
    大纲
    0.05
     Wszyst
    0.05
    Activations Density 0.001%

    No Known Activations