© 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. 24392
    Prev
    Next
    INDEX
    Explanations

    XQuery, XSLT, XPath technologies

    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
    å±ħ
    -0.07
    å±ħåīį
    -0.07
    ç½Ħ
    -0.07
    ä»
    -0.07
    Ey
    -0.06
    itage
    -0.06
    åħ·æľīä¸Ģå®ļçļĦ
    -0.06
    æĺ¯å¤©
    -0.06
     germ
    -0.06
     ratt
    -0.06
    POSITIVE LOGITS
     Techniques
    0.08
     techniques
    0.08
     technique
    0.08
     doubly
    0.08
     Technique
    0.07
    é¢Ħå¤ĦçIJĨ
    0.07
    _ROOT
    0.07
    uai
    0.07
    á»Ļt
    0.07
    alli
    0.07
    Activations Density 0.007%

    No Known Activations