© 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. 62089
    Prev
    Next
    INDEX
    Explanations

    thank you and more

    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
    aea
    -0.07
    汪汪
    -0.07
    ocat
    -0.07
    åįģåĽĽç«ł
    -0.07
    ek
    -0.07
    尼奥
    -0.07
    aired
    -0.07
    Edition
    -0.07
    ³³³³³³³³
    -0.07
     Feira
    -0.07
    POSITIVE LOGITS
     Porr
    0.07
    ium
    0.07
    urah
    0.07
    kön
    0.06
    oble
    0.06
    raina
    0.06
    acr
    0.06
    åĴĮæĬĢèĥ½
    0.06
    ä¸ŃæŃ£
    0.06
    è¿ĩ硬
    0.06
    Activations Density 0.511%

    No Known Activations