© 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. 10890
    Prev
    Next
    INDEX
    Explanations

    programming keywords

    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
    /etc
    -0.06
    ä¸ĭåIJĮ
    -0.06
    è
    -0.06
    YA
    -0.06
    asuk
    -0.06
    fer
    -0.06
    ä»»
    -0.06
    getter
    -0.06
    validator
    -0.06
    çĶŁåij½ç§ijåѦ
    -0.06
    POSITIVE LOGITS
    éĺħè¯»æľ¬æĸĩåīį
    0.09
    æľ¬æĸĩ为åįļ主
    0.08
    emy
    0.08
    åħ¨æľ¬å°ı说
    0.08
    ocache
    0.07
    OptionsResolver
    0.07
    ãĥĸãĥŃãĤ°æĿij
    0.07
    <quote
    0.07
    OfClass
    0.07
    ä¸įç»Ŀ
    0.07
    Activations Density 0.095%

    No Known Activations