© 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. 22181
    Prev
    Next
    INDEX
    Explanations

    account or cards structure

    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
    è®¤çľŁç»Ħç»ĩ
    -0.05
    ugin
    -0.05
     Noi
    -0.05
     Journey
    -0.05
    eturn
    -0.05
    ç»Ħç»ĩ建设
    -0.05
    Ñİ
    -0.05
    erville
    -0.05
    ç¬Ķ
    -0.05
     جÙĦÙĪ
    -0.05
    POSITIVE LOGITS
    离线
    0.06
    éĿĴéĿĴ
    0.06
    å¿Ĺ
    0.06
    iriam
    0.06
    æģ
    0.06
    æĺ¯æķ´ä¸ª
    0.06
    tent
    0.05
     sacr
    0.05
    ÙĪع
    0.05
    اÛĮÛĮ
    0.05
    Activations Density 0.001%

    No Known Activations