© 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. 18822
    Prev
    Next
    INDEX
    Explanations

    empty literals and structures

    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
    ä¿®
    -0.07
    ç®Ģ
    -0.05
     initial
    -0.05
     opt
    -0.05
     simplicity
    -0.05
     simplified
    -0.05
    èİİ
    -0.05
    ä¿®çļĦ
    -0.05
     safeguard
    -0.05
    æĬĦ
    -0.05
    POSITIVE LOGITS
    uct
    0.07
    ĺ
    0.06
    æĭİåĮħ
    0.06
    altezza
    0.06
    bih
    0.06
    æŶæ¯ı
    0.06
    éħ
    0.06
     véhic
    0.06
    ismatch
    0.06
    rgan
    0.06
    Activations Density 0.006%

    No Known Activations