© 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. 21733
    Prev
    Next
    INDEX
    Explanations

    large file sizes or units of measurement

    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
    åij¼åIJ¸éģĵæĦŁæŁĵ
    -0.05
    åĽłä¸ºè¿ĻäºĽ
    -0.05
    ç©Ģ
    -0.05
    ongan
    -0.05
    è¯ļ
    -0.05
     maggi
    -0.05
    shr
    -0.05
     exclus
    -0.05
    ’ét
    -0.05
    å¿ĥèĦıçĹħ
    -0.05
    POSITIVE LOGITS
    ensus
    0.06
    èĢĮåħ¶
    0.06
    ัà¸Ķ
    0.06
    æĺ¯ä¸Ģ大
    0.05
    èĢĮå¤į
    0.05
    äºİ人
    0.05
    ucer
    0.05
    itic
    0.05
    alth
    0.05
    äºĨæķ´ä¸ª
    0.05
    Activations Density 0.054%

    No Known Activations