© 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. 16891
    Prev
    Next
    INDEX
    Explanations

    rescue operations and teams

    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
     pa
    -0.06
     gent
    -0.06
    ÑĢек
    -0.06
    tum
    -0.06
    æĹı群
    -0.06
    ä¿
    -0.06
     تÙĤرÙĬب
    -0.06
    ceipt
    -0.05
     :(
    -0.05
    ä¸įçĶŁ
    -0.05
    POSITIVE LOGITS
    wick
    0.06
    æľīåĽ°éļ¾
    0.05
    ress
    0.05
    ãģĤ
    0.05
    ä½ľä¸ļ
    0.05
    _tar
    0.05
    ÑĮÑı
    0.05
    atsu
    0.05
    orpion
    0.05
     blind
    0.05
    Activations Density 0.029%

    No Known Activations