© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59822
    Prev
    Next
    INDEX
    Explanations

    African-American history, people, and culture

    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
    Negative Logits
     Austria
    -0.08
    å¥¥åľ°åĪ©
    -0.08
     Slovenia
    -0.08
     Sloven
    -0.08
     Alps
    -0.07
    ommel
    -0.07
     Narendra
    -0.07
    æ²
    -0.07
    åºIJå±±
    -0.07
     Switzerland
    -0.07
    POSITIVE LOGITS
    é»ij人
    0.18
     Afro
    0.15
     African
    0.15
     afro
    0.15
     racial
    0.13
     racially
    0.13
     Harlem
    0.13
    frican
    0.13
     african
    0.13
    éĿŀæ´²
    0.13
    Activations Density 0.737%

    No Known Activations