© 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. 2981
    Prev
    Next
    INDEX
    Explanations

    law firm

    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
    nya
    -0.09
    able
    -0.07
    æĢĢ
    -0.07
    ness
    -0.07
    theless
    -0.07
    ÙĩÙĪÙħ
    -0.07
    تÙĩ
    -0.07
    менÑĭ
    -0.06
    æ²½
    -0.06
    wur
    -0.06
    POSITIVE LOGITS
    è½¼
    0.09
    maz
    0.08
    iking
    0.08
    0.07
    pä
    0.07
    OnError
    0.07
    andro
    0.07
    odos
    0.07
    ç§įçļĦ
    0.07
    åľ¨ç»Ļ
    0.07
    Activations Density 0.002%

    No Known Activations