© 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. 46215
    Prev
    Next
    INDEX
    Explanations

    spots, patches, areas, lesions, stains

    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
    Tower
    -0.07
    à¸Ĭี
    -0.07
    tower
    -0.07
    é¦
    -0.07
     Tower
    -0.07
    turnstile
    -0.07
     rigged
    -0.07
     folding
    -0.07
    paged
    -0.07
    æįŀ
    -0.07
    POSITIVE LOGITS
     spots
    0.13
     areas
    0.13
    éĿ¢ç§¯çļĦ
    0.12
    éĿ¢ç§¯
    0.11
     patches
    0.11
    -spot
    0.11
     Areas
    0.11
     area
    0.11
    ä¸Ģå¤Ħ
    0.11
    éĿ¢ç§¯ä¸º
    0.11
    Activations Density 0.383%

    No Known Activations