© 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. 18284
    Prev
    Next
    INDEX
    Explanations

    update or delete statements

    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
    raw
    -0.06
    اÙĨÙĩ
    -0.06
     virgin
    -0.06
    resh
    -0.05
    azz
    -0.05
    ×ķ×Ĺ
    -0.05
    顺åºĶ
    -0.05
    ihat
    -0.05
    æĹłå¿Į
    -0.05
    ostr
    -0.05
    POSITIVE LOGITS
    bola
    0.06
    æ¯Ķåݻ年åIJĮæľŁ
    0.06
    çļĦåħ¶ä»ĸ
    0.06
    ativ
    0.06
    ç§ijåѦéĻ¢
    0.05
    ative
    0.05
     hao
    0.05
    é»Ħè¿ŀ
    0.05
    ague
    0.05
    oliv
    0.05
    Activations Density 0.014%

    No Known Activations