© 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. 40835
    Prev
    Next
    INDEX
    Explanations

    conjugation, transpose, complementary

    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
    nern
    -0.08
    ×Ĺ×ĵ
    -0.07
    ÙĬاب
    -0.07
    elm
    -0.07
    æľºæŀĦæĶ¹éĿ©
    -0.07
    legates
    -0.07
    é¾ĻéŨ
    -0.07
    สำà¹Ģรà¹ĩà¸Ī
    -0.07
    лиÑģÑĤов
    -0.07
    èĦ±é¢ĸ
    -0.07
    POSITIVE LOGITS
    íݸ
    0.07
    icky
    0.07
     Hola
    0.07
    arer
    0.07
    .outer
    0.06
    esson
    0.06
    _frac
    0.06
    佬
    0.06
    opts
    0.06
    orp
    0.06
    Activations Density 0.001%

    No Known Activations