© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 16596
    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
    Negative Logits
    空åīį
    -0.06
    æĿĸ
    -0.06
    orro
    -0.06
    lore
    -0.05
    laughter
    -0.05
     غÛĮر
    -0.05
    èĢĻ
    -0.05
    haust
    -0.05
    íĨµ
    -0.05
    stylesheet
    -0.05
    POSITIVE LOGITS
    rine
    0.05
    inach
    0.05
     side
    0.05
    uzione
    0.05
     gubern
    0.05
    _consts
    0.05
    >Action
    0.05
     meanwhile
    0.05
    arak
    0.05
    éħįçļĦ
    0.05
    Activations Density 0.000%

    No Known Activations