© 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. 19009
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    好åij¢
    -0.07
    اتÙĩا
    -0.06
    åĬŀå®ŀäºĭ
    -0.06
    ëįĶëĿ¼ê³łìļĶ
    -0.06
    sut
    -0.06
    atico
    -0.06
    è§ĤæŃ¢
    -0.06
    вÑĸв
    -0.06
    éįĽ
    -0.06
    代ä¹ĭ
    -0.06
    POSITIVE LOGITS
    éĢļè¿ĩåIJİ
    0.06
    -born
    0.05
    ools
    0.05
    ical
    0.05
    اÙĦÛĮ
    0.05
    ÙĦÙģØ©
    0.05
    ler
    0.05
    usan
    0.05
    ests
    0.05
    li
    0.05
    Activations Density 0.000%

    No Known Activations