© 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. 17524
    Prev
    Next
    INDEX
    Explanations

    incandescent, Chick-fil-A, config, Asian, real life

    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
    太çĻ½
    -0.08
    Past
    -0.07
    äºĨä¸ĭåİ»
    -0.07
     پرد
    -0.07
    žd
    -0.07
    æĹĹ
    -0.07
    æŀ·
    -0.07
     especiales
    -0.07
    OD
    -0.06
    ò
    -0.06
    POSITIVE LOGITS
    ufa
    0.08
    åIJĮç±»
    0.07
    åĴĮèĩªå·±
    0.07
    ç²¾ç¥ŀçļĦ
    0.06
    åĴĮèĩªå·±çļĦ
    0.06
    大å¸Ĥåľº
    0.06
    $v
    0.06
    кÑĢов
    0.06
    KS
    0.06
    kans
    0.06
    Activations Density 0.011%

    No Known Activations