© 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. 22620
    Prev
    Next
    INDEX
    Explanations

    by followed by names or titles

    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
    æĿ¥èĩª
    -0.06
    åĩºèĩª
    -0.05
    å¤ĸéĥ¨
    -0.05
    ¨
    -0.05
    å¤ĸåľ¨
    -0.05
    amu
    -0.05
    achte
    -0.05
    de
    -0.05
    Ø°
    -0.05
    ä¸įåIJĮ
    -0.05
    POSITIVE LOGITS
    ivec
    0.06
     ná»ķi
    0.06
    éļ¨æ©Ł
    0.06
    olik
    0.06
    æĺİãģij
    0.06
    çļĦä¿Ŀè¯ģ
    0.06
    вÑĭÑĪе
    0.06
    ãģ¤
    0.05
    ãĥĥãĥĪ
    0.05
    olated
    0.05
    Activations Density 0.080%

    No Known Activations