© 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. 47139
    Prev
    Next
    INDEX
    Explanations

    census data or statistics

    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
    osen
    -0.08
    åı£çº¢
    -0.07
     smooth
    -0.07
    byt
    -0.07
     поп
    -0.07
    åĴ¸å®ģ
    -0.07
    mat
    -0.07
    ickle
    -0.07
    ophon
    -0.07
    请æĮī
    -0.07
    POSITIVE LOGITS
    çł´è§£
    0.07
    bery
    0.06
    ll
    0.06
    strup
    0.06
    缴æİ¥æĬĬ
    0.06
    ãģ°ãģĭãĤĬ
    0.06
    eter
    0.06
    ä¿¡æģ¯è¿Ľè¡Į
    0.06
    aha
    0.06
     ÐľÐ°Ð»Ð¾
    0.06
    Activations Density 0.002%

    No Known Activations