© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21598
    Prev
    Next
    INDEX
    Explanations

    numerical and boolean constants

    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
    aji
    -0.08
     Rowe
    -0.07
    iqu
    -0.07
    ...,
    -0.06
    _cf
    -0.06
    hluk
    -0.06
    emann
    -0.06
    estina
    -0.06
    æ¥ļ
    -0.06
    èĬĬ
    -0.06
    POSITIVE LOGITS
    æĹ¢åı¯ä»¥
    0.08
    æĹ¢åı¯
    0.07
    å¿ĥæĢĢ
    0.07
    uszcz
    0.07
    vfs
    0.07
    sap
    0.07
    æĢ»ä¸įèĥ½
    0.07
    DED
    0.07
     manc
    0.07
    Ïģη
    0.07
    Activations Density 0.042%

    No Known Activations