© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 27110
    Prev
    Next
    INDEX
    Explanations

    text analysis and technical terms

    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
    ansch
    -0.07
     tabl
    -0.07
    stä
    -0.07
    æľ¬ç½ij
    -0.07
    çĽĪçĽĪ
    -0.07
    .qq
    -0.07
    isode
    -0.06
    ÙħÙĬÙĦ
    -0.06
    äº¬ä¸ľèĩªèIJ¥
    -0.06
    åįİè¯ŀ
    -0.06
    POSITIVE LOGITS
    SPA
    0.07
    ziale
    0.07
    èµ°çļĦ
    0.07
    èµ°çĿĢ
    0.07
    lek
    0.07
    ½Ķ
    0.07
    urch
    0.07
    Õ¬
    0.07
    ish
    0.06
    ender
    0.06
    Activations Density 0.010%

    No Known Activations