© 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. 40744
    Prev
    Next
    INDEX
    Explanations

    Slavic surnames and company suffixes

    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
    èĺij
    -0.08
    人å¤ļ
    -0.07
    utate
    -0.07
    аÑĤелÑĮно
    -0.07
     Mandarin
    -0.07
     Chinese
    -0.07
    äºĮ
    -0.07
    æ½¢
    -0.07
     NGX
    -0.07
    rzy
    -0.07
    POSITIVE LOGITS
     Sloven
    0.09
    ovic
    0.08
     Yugosl
    0.08
    oviÄĩ
    0.08
    Äĩ
    0.08
     Danilo
    0.08
     Serbia
    0.07
     Filip
    0.07
     Tito
    0.07
     aust
    0.07
    Activations Density 0.198%

    No Known Activations