© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15248
    Prev
    Next
    INDEX
    Explanations

    parentheses with questions or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    falt
    -0.08
    hest
    -0.07
    wad
    -0.07
    nyt
    -0.07
    uchos
    -0.07
    ubar
    -0.07
    .refs
    -0.07
    igor
    -0.07
    ç»´äºļ
    -0.07
    管çIJĨçŃī
    -0.07
    POSITIVE LOGITS
    åĩ¡æľ¬ç½ij注æĺİ
    0.07
    (PC
    0.07
    |array
    0.07
      ↵    ↵
    0.07
    ãĢĸ
    0.07
     Weih
    0.07
    ardo
    0.06
    ä¾Ŀä¾Ŀ
    0.06
     Cruise
    0.06
    opan
    0.06
    Activations Density 0.002%

    No Known Activations