© 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. 20536
    Prev
    Next
    INDEX
    Explanations

    ,

    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¸įè¨Ģ
    -0.06
    vel
    -0.05
    大ä¸Ģ
    -0.05
    boro
    -0.05
    ongs
    -0.05
    ä½ĵ
    -0.05
    анÑĭ
    -0.05
     об
    -0.05
    ì¡°ìĿĺ
    -0.05
    _addresses
    -0.05
    POSITIVE LOGITS
     rato
    0.07
    éĩıå°ij
    0.05
    å¾Īå¥ĩæĢª
    0.05
    夸å¥ĸ
    0.05
     behavior
    0.05
     služ
    0.05
    æĢ§åľ°
    0.05
     اÙĦÙħبارÙĥ
    0.05
    quet
    0.05
     complains
    0.05
    Activations Density 0.002%

    No Known Activations