© 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. 11669
    Prev
    Next
    INDEX
    Explanations

    U.S. Pat. No. numerical identifiers

    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
    sein
    -0.08
    sey
    -0.08
    zelfde
    -0.07
    داء
    -0.07
     thuẫn
    -0.07
    ermann
    -0.07
    صÙĪÙĦ
    -0.07
    adelph
    -0.07
    vern
    -0.07
    yle
    -0.07
    POSITIVE LOGITS
    oczyn
    0.09
    acruz
    0.09
    (sh
    0.08
     Petersburg
    0.08
    ä¸įæ¸Ŀ
    0.08
    astian
    0.08
    isbury
    0.08
    uggling
    0.08
    acular
    0.08
    modo
    0.08
    Activations Density 0.485%

    No Known Activations