© 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. 24228
    Prev
    Next
    INDEX
    Explanations

    South Africa and related geography

    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
    æ±Ģ
    -0.09
    .microsoft
    -0.08
    .jp
    -0.08
     Boston
    -0.08
    æ¹ĺ
    -0.08
    èĬĿåĬłåĵ¥
    -0.08
    authorize
    -0.08
    าศ
    -0.08
    ä¸ľäº¬
    -0.07
     Massachusetts
    -0.07
    POSITIVE LOGITS
    åįĹéĿŀ
    0.16
     Johannesburg
    0.12
     apartheid
    0.11
     Zimbabwe
    0.10
     Afrika
    0.09
     Adelaide
    0.09
    .za
    0.09
     Cape
    0.09
     South
    0.08
    veld
    0.08
    Activations Density 0.297%

    No Known Activations