© 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. 30124
    Prev
    Next
    INDEX
    Explanations

    registration and copyright and camera

    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±ķå¼Ģåħ¨éĥ¨
    -0.07
    оÑı
    -0.07
    绾ç»İ
    -0.06
    åīįèĢħ
    -0.06
     Ø¢Ùħر
    -0.06
    enten
    -0.06
    äºĨæĮĩ
    -0.06
     Pras
    -0.06
    ÑģÑĤÑĸ
    -0.06
    ils
    -0.06
    POSITIVE LOGITS
     thereof
    0.07
    两ä¸į误
    0.06
    toria
    0.06
    家åºĹ
    0.06
    TRL
    0.06
    è·Łä½ł
    0.06
    ype
    0.06
    imet
    0.06
     коÑĤоÑĢого
    0.06
    essen
    0.06
    Activations Density 0.804%

    No Known Activations