© 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. 56256
    Prev
    Next
    INDEX
    Explanations

    Apache License

    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
    arro
    -0.08
    -role
    -0.08
     xá»ī
    -0.07
    иÑģи
    -0.07
    ãĤīãģĦ
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    ieta
    -0.07
    asel
    -0.07
     =================================================
    -0.07
    ä¸Ģåĩº
    -0.07
    POSITIVE LOGITS
    urb
    0.08
    omot
    0.07
    Í
    0.07
    ï¸ı
    0.07
    uet
    0.07
    วม
    0.07
    ij
    0.07
    -lib
    0.07
    äºĽ
    0.07
    çĶ¨æĦı
    0.06
    Activations Density 0.009%

    No Known Activations