© 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. 16812
    Prev
    Next
    INDEX
    Explanations

    BOOST

    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
    示
    -0.05
    èµĦ
    -0.05
    éĤ£åıª
    -0.05
    ug
    -0.05
    ç½®
    -0.05
    èIJ¥
    -0.05
     gag
    -0.05
    oud
    -0.05
     esc
    -0.05
    åĪ©äºļ
    -0.05
    POSITIVE LOGITS
     McMaster
    0.06
    aterno
    0.06
    icana
    0.06
     kellett
    0.06
    enerd
    0.06
    ducted
    0.06
    ÑĩноÑģÑĤÑĮÑİ
    0.06
    æĬ¥åIJį人æķ°
    0.06
     Curitiba
    0.06
    anggar
    0.06
    Activations Density 0.008%

    No Known Activations