© 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. 33266
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific results

    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
     Karn
    -0.08
    áŀ¶áŀĶáŁĭ
    -0.08
    ertz
    -0.08
    anyi
    -0.08
    еÑĢна
    -0.08
    Ajax
    -0.07
    é£Ľãģ°
    -0.07
    trang
    -0.07
    åıªè¦ģæľī
    -0.07
    ç¿İ
    -0.07
    POSITIVE LOGITS
     famously
    0.08
    缮åīįå·²ç»ı
    0.07
     related
    0.07
    èijĹåIJįçļĦ
    0.07
    èijĹåIJį
    0.07
    缮åīįå·²
    0.07
    æľĢèijĹåIJįçļĦ
    0.07
     famous
    0.07
    è¿Ļ个æķ°åŃĹ
    0.07
     Misc
    0.06
    Activations Density 0.005%

    No Known Activations