© 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. 50965
    Prev
    Next
    INDEX
    Explanations

    technical terms or specific device components

    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
    bacher
    -0.08
    RED
    -0.08
    ensif
    -0.08
    èĢĹ
    -0.08
    ibes
    -0.08
    ughters
    -0.07
    ogi
    -0.07
    Äĥl
    -0.07
    ciano
    -0.07
    _FIN
    -0.07
    POSITIVE LOGITS
     plays
    0.06
    avit
    0.06
    (ur
    0.06
    âģ
    0.06
    ä¸įçŁ¥éģĵä½ł
    0.06
    润åıij
    0.05
    ç»Ļèĩªå·±çļĦ
    0.05
     Va
    0.05
    arian
    0.05
    æĹłå½¢çļĦ
    0.05
    Activations Density 0.111%

    No Known Activations