© 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. 16702
    Prev
    Next
    INDEX
    Explanations

    appointments, tickets, laptops, items, home, costs

    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
    Negative Logits
    .quant
    -0.06
     monot
    -0.05
     casse
    -0.05
    æĢ»ç«Ļ
    -0.05
    -stock
    -0.05
    çĭ¬æłĭ
    -0.05
    iá»ĩt
    -0.05
    .promise
    -0.05
    寸
    -0.05
    quant
    -0.05
    POSITIVE LOGITS
    å»ī
    0.06
    å»īä»·
    0.06
    iper
    0.06
     cheaper
    0.06
     cheap
    0.05
    ürk
    0.05
    èķ
    0.05
    ç»ĦåĴĮ
    0.05
    geg
    0.05
    _modules
    0.05
    Activations Density 0.008%

    No Known Activations