© 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. 16086
    Prev
    Next
    INDEX
    Explanations

    system.windows

    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
    _CONSTANT
    -0.07
    ambo
    -0.06
    achu
    -0.06
    çļĦå¥½åľ°æĸ¹
    -0.06
    æĪijåĴĮæĪijçļĦ
    -0.06
    _TYP
    -0.06
    çļĦåĪ°æĿ¥
    -0.06
    éĿĻå¿ĥ
    -0.06
    quez
    -0.06
    åijĺ
    -0.06
    POSITIVE LOGITS
    )row
    0.08
    reserve
    0.07
    .ERR
    0.07
    '](
    0.07
    æĬĬè¿Ļ
    0.07
    mayan
    0.07
    incer
    0.07
    ycop
    0.07
    )value
    0.07
     ($("#
    0.07
    Activations Density 0.003%

    No Known Activations