© 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. 45409
    Prev
    Next
    INDEX
    Explanations

    newline after

    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
    ickness
    -0.07
    æĮ½
    -0.07
    家åĸ»
    -0.07
    以身
    -0.07
    èĥ½æī¾åĪ°
    -0.07
    åįĬæķ°
    -0.07
    à¸ļาล
    -0.07
    ante
    -0.07
    æĺ¯åı¯
    -0.07
    held
    -0.06
    POSITIVE LOGITS
    imak
    0.08
    æ¯ıé¢ĺ
    0.07
    bage
    0.07
     followed
    0.07
    çļĦåĬĽåº¦
    0.07
     trailing
    0.07
    eda
    0.07
    ä¹Łå¥½
    0.07
    uml
    0.07
    ç»įåħ´
    0.07
    Activations Density 0.011%

    No Known Activations