© 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. 18874
    Prev
    Next
    INDEX
    Explanations

    court documents

    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
    ÙĨدÙĩ
    -0.07
    andalkan
    -0.06
    tid
    -0.06
    ALLERY
    -0.05
    warts
    -0.05
    èħĨ
    -0.05
    idt
    -0.05
     kalkul
    -0.05
    иÑĢов
    -0.05
     Sanctuary
    -0.05
    POSITIVE LOGITS
    Ùĩج
    0.06
    æľ¬æĬ¥
    0.06
    ums
    0.06
    å¾ĹåĪ°çļĦ
    0.05
    çľĭæ³ķ
    0.05
    um
    0.05
    çĻ»å½ķåIJİ
    0.05
    arat
    0.05
    æ·ĭæ¼ĵå°½
    0.05
     Melee
    0.05
    Activations Density 0.001%

    No Known Activations