© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 40639
    Prev
    Next
    INDEX
    Explanations

    peak values, records, or deviations

    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
    æīİæīİå®ŀ
    -0.08
    gados
    -0.07
    _INITIALIZER
    -0.07
    å·¥é¾Ħ
    -0.07
    çĤ¯
    -0.07
    olland
    -0.07
    声ä¸Ń
    -0.07
    檸
    -0.07
    askan
    -0.06
    æĪİ
    -0.06
    POSITIVE LOGITS
     peak
    0.13
    peak
    0.12
    å³°åĢ¼
    0.12
    æľĢé«ĺçĤ¹
    0.12
    æľĢé«ĺ
    0.11
     peaks
    0.10
    顶峰
    0.10
     puncak
    0.10
    สูà¸ĩสุà¸Ķ
    0.10
    é«ĺå³°
    0.10
    Activations Density 0.082%

    No Known Activations