© 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. 19088
    Prev
    Next
    INDEX
    Explanations

    will be

    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
     непÑĢе
    -0.07
    aline
    -0.07
    cito
    -0.06
    åĸĿä¸ĢæĿ¯
    -0.06
    cias
    -0.06
    olis
    -0.06
    æľ¬ä¼ģä¸ļ
    -0.06
    ulik
    -0.06
    bang
    -0.06
    itesse
    -0.06
    POSITIVE LOGITS
     favor
    0.07
    ª
    0.06
    æī¿è½½
    0.06
    ç»ĵ
    0.06
     عÙħÙĦ
    0.05
    éĢļ
    0.05
    Ùĭ
    0.05
     char
    0.05
    çµIJ
    0.05
    被
    0.05
    Activations Density 0.018%

    No Known Activations