© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19604
    Prev
    Next
    INDEX
    Explanations

    ambiance or ambient atmosphere

    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
    Them
    -0.05
    tesi
    -0.05
    æĥĬ
    -0.05
    cken
    -0.05
    kits
    -0.05
    zÄĻ
    -0.05
    ][(
    -0.05
    ä¸ĢåĽŀäºĭ
    -0.05
     Them
    -0.05
    Ú¯ÙĪÙĨÙĩ
    -0.05
    POSITIVE LOGITS
     course
    0.06
    nie
    0.06
    elop
    0.06
    æł¼æĭī
    0.06
    eping
    0.06
    nis
    0.06
    uin
    0.05
    KK
    0.05
    éĶħåºķ
    0.05
    беÑĢ
    0.05
    Activations Density 0.001%

    No Known Activations