© 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. 22549
    Prev
    Next
    INDEX
    Explanations

    missed opportunities

    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
    ingan
    -0.07
    移æ°ijå±Ģ
    -0.06
    оÑģÑģ
    -0.06
    mana
    -0.06
    azon
    -0.06
    okol
    -0.06
    ariana
    -0.06
    eros
    -0.06
    å°ı家
    -0.06
    åħ·ä½ĵæݪæĸ½
    -0.06
    POSITIVE LOGITS
    éĺ»å¡ŀ
    0.06
     opportunities
    0.05
    éĶĻè¿ĩ
    0.05
    æľºä¼ļ
    0.05
    íĻľ
    0.05
    åķĨæľº
    0.05
    æݢ索
    0.05
     nast
    0.05
     luk
    0.05
    ç»ıéªĮ
    0.05
    Activations Density 0.011%

    No Known Activations