© 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. 42884
    Prev
    Next
    INDEX
    Explanations

    information and details

    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
    ç±»åŀĭ为
    -0.08
    öz
    -0.07
    resto
    -0.07
    evin
    -0.07
    haw
    -0.07
    ãģ®åĩº
    -0.07
    watan
    -0.07
    è´¯éĢļ
    -0.07
    fred
    -0.07
    สัà¸ģ
    -0.07
    POSITIVE LOGITS
    æŁIJäºĽ
    0.09
    éĩİ
    0.08
     nuances
    0.08
    æĸ¤
    0.08
     aspects
    0.07
    ®
    0.07
     details
    0.07
    对ä¸ĢäºĽ
    0.07
    ç»ĨèĬĤ
    0.07
     rẽ
    0.07
    Activations Density 0.275%

    No Known Activations