© 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. 16604
    Prev
    Next
    INDEX
    Explanations

    querying database collections

    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
    én
    -0.06
    nius
    -0.06
    urian
    -0.05
    ican
    -0.05
    غر
    -0.05
    itie
    -0.05
    ABCDEFG
    -0.05
     reliance
    -0.05
    yna
    -0.05
    è½¬æľº
    -0.05
    POSITIVE LOGITS
    resta
    0.06
    ages
    0.06
    uzu
    0.06
    çIJ³å¨ľ
    0.06
    à¸Łà¸´à¸ģ
    0.06
    ç£Ĭ
    0.06
    _Style
    0.06
    addy
    0.05
    ç´¯
    0.05
    æ¥ł
    0.05
    Activations Density 0.008%

    No Known Activations