© 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. 48271
    Prev
    Next
    INDEX
    Explanations

    spline transformation

    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
    å¤įå¼ı
    -0.08
    ÚĨار
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    åīĶéĢı
    -0.07
    owler
    -0.07
    人寿
    -0.06
    ipheral
    -0.06
    _SCRIPT
    -0.06
    ruise
    -0.06
    .Target
    -0.06
    POSITIVE LOGITS
    éĿ¡
    0.07
     tension
    0.07
    èįī
    0.07
    æ°´ä¸Ń
    0.07
    lieder
    0.07
     Sob
    0.07
    ạc
    0.07
    acular
    0.07
    ç¾İåĮĸ
    0.07
    bill
    0.07
    Activations Density 0.009%

    No Known Activations