© 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. 14599
    Prev
    Next
    INDEX
    Explanations

    terms of licenses

    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
    åIJįæĢĿ
    -0.08
    scha
    -0.08
     Unters
    -0.07
    quel
    -0.07
    removeClass
    -0.07
    天éķ¿
    -0.07
    ÑĢного
    -0.07
     láºŃp
    -0.07
    ãĥªãĤ¨
    -0.07
    æłĸéľŀ
    -0.07
    POSITIVE LOGITS
     EITHER
    0.07
    å½ĵå¹´çļĦ
    0.07
    _framework
    0.07
    cak
    0.07
    ÑģловиÑı
    0.06
    licenses
    0.06
    ·
    0.06
    æľįåĬ¡åįıè®®
    0.06
     Gim
    0.06
    ult
    0.06
    Activations Density 0.932%

    No Known Activations