© 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. 18846
    Prev
    Next
    INDEX
    Explanations

    Boston and Massachusetts

    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
    æİĮ
    -0.07
    aeda
    -0.07
    baugh
    -0.07
    sstr
    -0.06
     Mesa
    -0.06
    ledged
    -0.06
    irati
    -0.06
    ISCO
    -0.06
    åºķæĿ¿
    -0.06
     Mondi
    -0.06
    POSITIVE LOGITS
    Boston
    0.07
     Boston
    0.07
     Massachusetts
    0.07
    achusetts
    0.07
    麻çľģ
    0.07
    us
    0.06
    ic
    0.06
    est
    0.06
    波士顿
    0.06
    ype
    0.06
    Activations Density 0.131%

    No Known Activations