© 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. 47550
    Prev
    Next
    INDEX
    Explanations

    Virginia, Mozilla, and legal citations

    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
     Zür
    -0.10
    ä¹Ŀæ±Ł
    -0.09
     Finnish
    -0.09
     Iranians
    -0.09
     finland
    -0.08
    大é¹ı
    -0.08
    zep
    -0.08
    èĬ¬åħ°
    -0.08
    åºIJå±±
    -0.08
     Bombay
    -0.08
    POSITIVE LOGITS
     Virginia
    0.12
     Recife
    0.12
    Virginia
    0.11
     Charlottesville
    0.10
     Maryland
    0.10
    éģµä¹ī
    0.10
     mozilla
    0.09
     Pernamb
    0.09
    Mozilla
    0.09
     Baltimore
    0.09
    Activations Density 0.854%

    No Known Activations