© 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. 16861
    Prev
    Next
    INDEX
    Explanations

    months and dates

    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
    çŁ¾
    -0.06
    ÙĦب
    -0.06
    ç¼ł
    -0.06
     forthcoming
    -0.06
    kada
    -0.06
    èijĨ
    -0.06
    çIJħ
    -0.06
    Amministrazione
    -0.06
    oux
    -0.06
      ↵    ↵
    -0.06
    POSITIVE LOGITS
    éķ¿æŀª
    0.05
    IANO
    0.05
    çļĦæľĢé«ĺ
    0.05
     pane
    0.05
     ramp
    0.05
     ref
    0.05
    sect
    0.05
     maximum
    0.05
     shade
    0.05
     exped
    0.05
    Activations Density 0.118%

    No Known Activations