© 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. 22208
    Prev
    Next
    INDEX
    Explanations

    countries and regions

    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¿ĩ度
    -0.05
     toda
    -0.05
    Im
    -0.05
    icontains
    -0.05
    ite
    -0.05
    rz
    -0.04
    æĺ¾çĿĢ
    -0.04
    æĶ
    -0.04
    åĴĮ使çĶ¨
    -0.04
    ä¸įèĥ½ä½¿çĶ¨
    -0.04
    POSITIVE LOGITS
    åľ¨éĤ£éĩĮ
    0.07
    ongi
    0.07
    ushman
    0.06
    кок
    0.06
     dort
    0.06
    osals
    0.06
    gings
    0.06
    Perm
    0.06
     ÑĤам
    0.06
     ÙħعÙĩا
    0.06
    Activations Density 0.006%

    No Known Activations