© 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. 33248
    Prev
    Next
    INDEX
    Explanations

    Ricci curvature

    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
    tier
    -0.07
    oret
    -0.06
     ë°ĶëŀĮ
    -0.06
    oire
    -0.06
    åįĬå°ıæŶ
    -0.06
    约å®ļçļĦ
    -0.06
     vetro
    -0.06
    жеÑĢе
    -0.06
    åįĬæŃ¥
    -0.06
    egni
    -0.06
    POSITIVE LOGITS
     tensor
    0.08
    tensor
    0.08
    éĻħ
    0.08
    ×ķ×ĵ
    0.08
     tensors
    0.08
    大åĸľ
    0.07
    åħ¬æĬ¥
    0.07
    heed
    0.07
    漩涡
    0.07
    riad
    0.07
    Activations Density 0.005%

    No Known Activations