© 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. 16546
    Prev
    Next
    INDEX
    Explanations

    Corporate announcements and medical conditions

    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
    arto
    -0.06
    oku
    -0.06
     Power
    -0.06
    hands
    -0.05
    åĻ¨çŃī
    -0.05
    akan
    -0.05
    à¸Ķà¸Ķ
    -0.05
    å¢ŀ产
    -0.05
     MOD
    -0.05
     P
    -0.05
    POSITIVE LOGITS
    æĦıå¤ĸ
    0.06
    夫æĸ¯åŁº
    0.06
     Henrique
    0.06
    uced
    0.06
    endid
    0.06
    agos
    0.06
    otal
    0.06
    ske
    0.06
     Ekon
    0.05
     CSRF
    0.05
    Activations Density 0.008%

    No Known Activations