© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19419
    Prev
    Next
    INDEX
    Explanations

    stay

    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
    unte
    -0.07
    utip
    -0.06
    odus
    -0.06
    ulut
    -0.06
    ä¸įè¦ģå¿ĺäºĨ
    -0.06
    两ä¸į误
    -0.06
    鼷æĸ¯
    -0.06
    ole
    -0.06
    ulte
    -0.06
    à¹Ģวียà¸Ļ
    -0.06
    POSITIVE LOGITS
    æĮ½çķĻ
    0.07
    çķĻä¸ĭæĿ¥
    0.06
    çķĻä½ı
    0.06
     cond
    0.06
    cond
    0.05
    Cond
    0.05
    éĻĦåĬł
    0.05
    åĬĽ
    0.05
    -cond
    0.05
    ist
    0.05
    Activations Density 0.033%

    No Known Activations