© 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. 46077
    Prev
    Next
    INDEX
    Explanations

    number format

    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
    çİĭä¹ĭ
    -0.07
    inte
    -0.07
    /do
    -0.07
    尼奥
    -0.07
    of
    -0.06
    age
    -0.06
    ç©·
    -0.06
    kis
    -0.06
    éĢĶç»ı
    -0.06
    ä¸īäºĶ
    -0.06
    POSITIVE LOGITS
    èıģ
    0.08
    ç½ijçĽĺ
    0.07
    大å±Ģ
    0.07
    åįİ西
    0.07
    åįİéĺ³
    0.07
    weiler
    0.07
    èĢĮåĸ»
    0.06
    ä»Ĭå¤©åľ¨
    0.06
    hofer
    0.06
    arena
    0.06
    Activations Density 0.002%

    No Known Activations