© 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. 18694
    Prev
    Next
    INDEX
    Explanations

    auxiliary verbs followed by infinitives or 'be'

    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
    urez
    -0.05
    ugd
    -0.05
    utar
    -0.05
    æĭĽåķĨ
    -0.05
    ç§ģæľį
    -0.05
    otur
    -0.05
    erp
    -0.05
     تخصص
    -0.05
    ien
    -0.05
    würd
    -0.05
    POSITIVE LOGITS
    ìĩĦ
    0.06
    æ·¼
    0.06
    öst
    0.06
    讳
    0.06
    ä¸Ģå¾ĭ
    0.05
    izontal
    0.05
    Kami
    0.05
    ï¼īãĥ»
    0.05
    ืà¸Ńà¸ĩ
    0.05
    æķĪåĬĽçļĦ
    0.05
    Activations Density 0.019%

    No Known Activations