© 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. 24453
    Prev
    Next
    INDEX
    Explanations

    dates, specific words, and numbers

    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
    èľĤ
    -0.08
    ç«ĭ
    -0.07
    bran
    -0.07
    cida
    -0.07
     sucess
    -0.07
    pii
    -0.07
    å®ī
    -0.07
    ptest
    -0.07
    asje
    -0.07
    pike
    -0.07
    POSITIVE LOGITS
     titular
    0.07
    ornos
    0.07
    anner
    0.07
    ÙĤÙħ
    0.07
    å®ļä¹ī为
    0.06
    oven
    0.06
    纬
    0.06
    ustom
    0.06
     Late
    0.06
     Viên
    0.06
    Activations Density 0.264%

    No Known Activations