© 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. 47210
    Prev
    Next
    INDEX
    Explanations

    countries and 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
     Schweizer
    -0.07
    èm
    -0.07
    wers
    -0.07
    å¦ĤæѤä¹ĭ
    -0.07
    leps
    -0.07
    æĮĩçļĦ
    -0.07
    åī¯åĮºéķ¿
    -0.06
    bservice
    -0.06
    åĴĮè§ĦèĮĥ
    -0.06
    ÙĪÛĮÙĩ
    -0.06
    POSITIVE LOGITS
    å¢ĥåĨħçļĦ
    0.10
     nationals
    0.09
    çŃīåĽ½
    0.08
    anse
    0.08
     Republic
    0.08
    å®ĺæĸ¹
    0.08
    æľ¬åĽ½
    0.08
    çŃīåĽ½å®¶
    0.07
    åİĨåı²ä¸ĬçļĦ
    0.07
    åıĬåij¨è¾¹
    0.07
    Activations Density 0.371%

    No Known Activations