© 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. 22278
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
    çģŃäºĨ
    -0.06
    aries
    -0.06
    é£ŀæĿ¥
    -0.05
    arius
    -0.05
    ç«ĭåľº
    -0.05
     weken
    -0.05
    parameters
    -0.05
    azza
    -0.05
    åİĨ代
    -0.05
    éģ¥
    -0.05
    POSITIVE LOGITS
    ician
    0.06
    à¸ģร
    0.06
    ãģİ
    0.06
     Insomma
    0.06
    æĵįä½ľä¸Ĭ
    0.06
     raf
    0.06
    ocus
    0.06
    chn
    0.05
    ÙĪرت
    0.05
    inc
    0.05
    Activations Density 0.002%

    No Known Activations