© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21785
    Prev
    Next
    INDEX
    Explanations

    second fundamental form

    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
     thy
    -0.07
    _tail
    -0.07
    究
    -0.07
    çĶľçĶľçļĦ
    -0.07
    çIJ¥çıĢ
    -0.07
     overnight
    -0.07
     single
    -0.07
     disag
    -0.07
    yled
    -0.07
    éĺ
    -0.07
    POSITIVE LOGITS
    patches
    0.09
     patches
    0.08
     surfaces
    0.08
    urface
    0.08
    surface
    0.08
    表éĿ¢çļĦ
    0.08
    Surface
    0.08
     Surface
    0.08
    泡
    0.07
    ä¸ĢéĿ¢
    0.07
    Activations Density 0.013%

    No Known Activations