© 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. 18832
    Prev
    Next
    INDEX
    Explanations

    ac words and their completions

    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
    åħ¥å¾®
    -0.08
    ez
    -0.08
    ation
    -0.08
    pread
    -0.07
    Ø©
    -0.07
    eur
    -0.07
    æ¯Ķå¦Ĥåľ¨
    -0.07
    chaft
    -0.07
    alog
    -0.07
    naire
    -0.06
    POSITIVE LOGITS
    ILITY
    0.07
    OUNTRY
    0.06
    VERTISEMENT
    0.06
    ocks
    0.06
        ↵    ↵    ↵    ↵
    0.06
    öffnet
    0.06
    身ä¸Ĭä¸ĭ
    0.06
    stm
    0.06
    ÑĦикÑģи
    0.06
     INTERNA
    0.06
    Activations Density 0.075%

    No Known Activations