© 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. 20991
    Prev
    Next
    INDEX
    Explanations

    selfies, bowling, arcade, entertainment

    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
    åħ¥å¾®
    -0.07
    æĴŃ
    -0.06
    _FEED
    -0.06
    нÑĸка
    -0.06
    ements
    -0.06
    ãi
    -0.06
    ç»ĨåĪĻ
    -0.06
    åij¨äºĮ
    -0.06
     handleClick
    -0.06
    åħ¥å®¤
    -0.06
    POSITIVE LOGITS
    azzo
    0.06
    hang
    0.05
    дÑĢ
    0.05
    éĿĴæĺ¥
    0.05
    itzer
    0.05
     пол
    0.05
    ystal
    0.05
    ub
    0.05
     Broadway
    0.05
    icket
    0.05
    Activations Density 0.003%

    No Known Activations