© 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. 56763
    Prev
    Next
    INDEX
    Explanations

    academic and professional fields

    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
    è¶Ĭ
    -0.06
    alise
    -0.06
    åīĶ
    -0.06
    asma
    -0.06
    -badge
    -0.06
    汽水
    -0.06
    æīĢåľ¨åįķä½į
    -0.06
    _baseline
    -0.06
    utra
    -0.06
    DAQ
    -0.06
    POSITIVE LOGITS
    ä¸ŃçļĦåºĶçĶ¨
    0.10
    ä¸ŃçļĦä½ľçĶ¨
    0.09
    åºĶçĶ¨ä¸Ń
    0.08
    ä¹Łç»ı常
    0.08
    æ¯Ķè¾ĥå¤ļ
    0.08
    ä¸įè¯Ĩ
    0.08
    éĤ£è¾¹
    0.08
    ãģ«ãģĬãģĦãģ¦ãģ¯
    0.08
    ãģ«ãģĬãģĦãģ¦
    0.08
    ä¸įå°ijçļĦ
    0.08
    Activations Density 0.153%

    No Known Activations