© 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. 22504
    Prev
    Next
    INDEX
    Explanations

    checking from which floor

    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
    _spinner
    -0.08
    æİł
    -0.07
    uschen
    -0.07
    iett
    -0.07
    ä¸įäºĮ
    -0.07
    airy
    -0.07
    -parser
    -0.07
    λÏİ
    -0.07
    ibra
    -0.07
     ÙĨظ
    -0.07
    POSITIVE LOGITS
    åĪļåĪļ好
    0.08
    æĺ¯æľĢ大çļĦ
    0.08
    icken
    0.08
    令第
    0.07
    æľĢåIJİä¸Ģ个
    0.07
    è¿ĺä¸įå¤Ł
    0.07
    ä¸įèĥ½åĨį
    0.07
    åªĴ
    0.07
    ä½Ĩä¸įèĥ½
    0.07
    èĬľ
    0.07
    Activations Density 0.041%

    No Known Activations