© 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. 27096
    Prev
    Next
    INDEX
    Explanations

    unit/number conversions

    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
    åIJĮå±ħ
    -0.07
    ledge
    -0.07
    eba
    -0.07
    _generated
    -0.06
    assy
    -0.06
    äºĴ
    -0.06
    kung
    -0.06
    xt
    -0.06
    (async
    -0.06
    æ´Ĵ
    -0.06
    POSITIVE LOGITS
    ects
    0.08
    uha
    0.07
     Ware
    0.07
    usses
    0.07
    æĺ¥æĿ¥
    0.07
    ætter
    0.07
    鼷ç¥ŀ
    0.07
    ësh
    0.07
    ILog
    0.07
    TypeInfo
    0.07
    Activations Density 0.317%

    No Known Activations