© 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. 33309
    Prev
    Next
    INDEX
    Explanations

    detection method or process

    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
    /her
    -0.09
    endale
    -0.08
    atically
    -0.08
    eldon
    -0.07
    èºĩ
    -0.07
    mern
    -0.07
    তà§ĩ
    -0.07
    Äħcz
    -0.07
    arer
    -0.07
    elda
    -0.07
    POSITIVE LOGITS
    OrCreate
    0.13
    åĪ°çļĦ
    0.11
    åĻ¨çļĦ
    0.09
    OrElse
    0.09
    åĴĮå¤ĦçIJĨ
    0.09
    /report
    0.09
     má»ıi
    0.08
    ürn
    0.08
    AndServe
    0.08
    à¸ģารà¸ĵà¹Į
    0.08
    Activations Density 0.035%

    No Known Activations