© 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. 22500
    Prev
    Next
    INDEX
    Explanations

    writing and written records

    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
    æIJŃ
    -0.07
    edly
    -0.06
    ç«ŀäºīé£İéĻ©
    -0.06
    èİ·åıĸæĽ´å¤ļ
    -0.06
    lé
    -0.06
     quoted
    -0.06
    æģ
    -0.05
    æĿ¥æºIJäºİ
    -0.05
     Licensed
    -0.05
     lic
    -0.05
    POSITIVE LOGITS
    пиÑģÑĮ
    0.06
    åıijæĸĩ
    0.06
    ehand
    0.05
    pond
    0.05
    æĶ¶åıij
    0.05
    hein
    0.05
     passive
    0.05
    ukai
    0.05
     Pun
    0.05
     sender
    0.05
    Activations Density 0.008%

    No Known Activations