© 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. 21996
    Prev
    Next
    INDEX
    Explanations

    nationalities

    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
    åĴĮæĮĩ导
    -0.09
    /dis
    -0.08
    ily
    -0.08
    tock
    -0.08
    æĪĸå°ij
    -0.07
    ãģĭãģ®
    -0.07
    usher
    -0.07
    aat
    -0.07
     ë§Īì°¬
    -0.07
    acket
    -0.07
    POSITIVE LOGITS
    -American
    0.11
    åĴĮæĹ¥æľ¬
    0.10
    -Israel
    0.10
    åĴĮç¾İåĽ½
    0.10
    apolis
    0.10
    -born
    0.09
    -themed
    0.09
    -Russian
    0.09
    åĴĮä¸ŃåĽ½
    0.09
    -Pacific
    0.08
    Activations Density 0.938%

    No Known Activations