© 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. 3559
    Prev
    Next
    INDEX
    Explanations

    patent numbers A1, B1

    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
    ÏĢÏĦÏīÏĥη
    -0.07
    áĥĺáĥĵ
    -0.07
    ê²łëĭ¤
    -0.06
    adier
    -0.06
    ÙĨØ´
    -0.06
    olla
    -0.06
    ÑħозÑıй
    -0.06
     Mercer
    -0.06
    folge
    -0.06
    boxing
    -0.06
    POSITIVE LOGITS
    дей
    0.07
    榨
    0.07
    dda
    0.07
    åIJĥ鸡
    0.06
    游人
    0.06
     dealt
    0.06
     viá»ĩc
    0.06
    ikkan
    0.06
     cifra
    0.06
     deals
    0.06
    Activations Density 0.193%

    No Known Activations