© 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. 40423
    Prev
    Next
    INDEX
    Explanations

    vegetables and produce

    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
    ç¾Ĭæ¯Ľ
    -0.08
     chocol
    -0.08
     flutter
    -0.07
    åij¨çijľ
    -0.07
    é¦Ļçģ«
    -0.07
     Espresso
    -0.07
    éħĿ
    -0.07
     chocolat
    -0.07
     banking
    -0.07
     coffee
    -0.07
    POSITIVE LOGITS
    çĪ½åı£
    0.09
    大æ£ļ
    0.09
     gigante
    0.08
    èĮİ
    0.08
    çĪ½
    0.07
    ucchini
    0.07
    æĬ¤çľ¼
    0.07
    èĶĵ
    0.07
    èIJ¥åħ»ä»·åĢ¼
    0.07
    è¿ĽåŁİ
    0.07
    Activations Density 0.072%

    No Known Activations