© 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. 18938
    Prev
    Next
    INDEX
    Explanations

    non-English words

    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
    ette
    -0.07
    æīİ
    -0.07
    antan
    -0.06
    rade
    -0.06
    /live
    -0.05
    æ´»
    -0.05
     ngá»Ļt
    -0.05
    moto
    -0.05
    TA
    -0.05
    quê
    -0.05
    POSITIVE LOGITS
    urs
    0.06
    ustin
    0.06
    аÑģÑĤо
    0.06
    enes
    0.06
     клÑİÑĩ
    0.06
     подÑģ
    0.05
     Cái
    0.05
    EDO
    0.05
    éĿĴé¾Ļ
    0.05
    HEY
    0.05
    Activations Density 0.031%

    No Known Activations