© 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. 18077
    Prev
    Next
    INDEX
    Explanations

    arabic and other languages

    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
     xì
    -0.08
    variably
    -0.07
     ï¿¥
    -0.07
    严äºİ
    -0.07
    osl
    -0.07
    quia
    -0.07
    影幽
    -0.07
    åIJįæĢĿ
    -0.07
    iams
    -0.07
    ojis
    -0.07
    POSITIVE LOGITS
    æĸ°åŁİ
    0.06
     up
    0.05
    対
    0.05
    åŁİ
    0.05
    \n
    0.05
    ,
    0.05
    æ´ĭèij±
    0.04
    [
    0.04
    —
    0.04
     immediately
    0.04
    Activations Density 0.005%

    No Known Activations