© 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. 8520
    Prev
    Next
    INDEX
    Explanations

    Roman history and figures

    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
     Fukushima
    -0.08
    西åħ°
    -0.08
    aket
    -0.08
    rogen
    -0.08
     Watt
    -0.08
    èĬ¥
    -0.08
    油箱
    -0.08
    zuki
    -0.08
     Kawasaki
    -0.08
     gamm
    -0.07
    POSITIVE LOGITS
     Roman
    0.14
     Romans
    0.12
     Rome
    0.12
    Roman
    0.12
     ë¡ľë§Ī
    0.12
     ÑĢим
    0.11
    Latin
    0.11
     Latin
    0.11
    ç½Ĺ马
    0.11
     Caesar
    0.10
    Activations Density 0.069%

    No Known Activations