© 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. 19933
    Prev
    Next
    INDEX
    Explanations

    goals and strategy

    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
    å·¥æľŁ
    -0.06
    uret
    -0.05
    æį¢ä½į
    -0.05
    æ¯ĽçĹħ
    -0.05
    弯弯
    -0.05
     IC
    -0.05
    汹汹
    -0.05
    æ¨¡æł·
    -0.05
    ponent
    -0.05
    habit
    -0.05
    POSITIVE LOGITS
    æĸ¹åIJijåĴĮ
    0.06
    大é£İ
    0.06
    æĸ¹åIJij
    0.06
    æ´»åĬĽ
    0.06
     phép
    0.06
    åIJĪ
    0.06
    ç»ıèIJ¥ç®¡çIJĨ
    0.05
    èĥ½éĩı
    0.05
    åħ¨å±Ģ
    0.05
    æĸ¹åIJijçļĦ
    0.05
    Activations Density 0.010%

    No Known Activations