© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21539
    Prev
    Next
    INDEX
    Explanations

    catchy song descriptions

    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
    çļĦåı¯
    -0.06
    åĽ½åĢº
    -0.06
     immediate
    -0.05
    Õ«ÖĢ
    -0.05
     rethink
    -0.05
    olak
    -0.05
    rung
    -0.05
     Instant
    -0.05
    odzi
    -0.05
     instant
    -0.05
    POSITIVE LOGITS
    лиз
    0.07
    hausen
    0.06
    åĮĸ管çIJĨ
    0.06
    ioned
    0.05
    perimental
    0.05
    lij
    0.05
    ithe
    0.05
    表达æĸ¹å¼ı
    0.05
    éĿŀåħ¬
    0.05
    她表示
    0.05
    Activations Density 0.003%

    No Known Activations