© 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. 18274
    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
    ابÙĩ
    -0.05
     vio
    -0.05
    âĢ
    -0.05
    b
    -0.05
     signature
    -0.05
    signature
    -0.05
     governing
    -0.05
     combination
    -0.05
    iscos
    -0.05
    ield
    -0.05
    POSITIVE LOGITS
    bum
    0.06
    ücks
    0.06
    æĻĴ
    0.06
    ä¸įç»Ŀ
    0.06
    cé
    0.06
     ('
    0.06
    æĬĽå¼ĥ
    0.05
    æ¯ĶåĪ«äºº
    0.05
    pad
    0.05
    æ¯ĶæĻ®éĢļ
    0.05
    Activations Density 0.000%

    No Known Activations