© 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. 27902
    Prev
    Next
    INDEX
    Explanations

    embed this page

    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
    [strlen
    -0.06
    teo
    -0.06
     à¸ķรà¸ĩ
    -0.06
    á»ķ
    -0.06
    å·±
    -0.06
    é¦ĸéķ¿
    -0.06
     nepr
    -0.06
    ç§ijåѦéĻ¢
    -0.06
    elus
    -0.06
    /auth
    -0.06
    POSITIVE LOGITS
    è¾Ĺ
    0.08
    ÙĪاØŃ
    0.07
     componentName
    0.07
    CADE
    0.07
    åįİå¾·
    0.07
    äºĨè¿Ľåİ»
    0.07
    ÑĤоÑĢи
    0.07
    åĨĴ
    0.07
    istogram
    0.07
    å¼ĢæĶ¾
    0.07
    Activations Density 0.073%

    No Known Activations