© 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. 18738
    Prev
    Next
    INDEX
    Explanations

    as ... evolves, continues, grows, becomes, rolled, has, Millennials

    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
    owering
    -0.06
    owers
    -0.06
    orean
    -0.06
    .vn
    -0.06
    entine
    -0.06
     polec
    -0.05
     ê°ĻìĿ´
    -0.05
    _SUFFIX
    -0.05
    ä¸įåı¯æĬĹåĬĽ
    -0.05
    ieten
    -0.05
    POSITIVE LOGITS
    anos
    0.06
     reality
    0.06
    issy
    0.06
    yc
    0.06
    валÑĮ
    0.05
    oper
    0.05
    ighted
    0.05
    laz
    0.05
    nu
    0.05
    tiqu
    0.05
    Activations Density 0.044%

    No Known Activations