© 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. 40903
    Prev
    Next
    INDEX
    Explanations

    afternoon time notation

    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
    尼迪
    -0.08
    åīįåºĶ
    -0.08
    éħİ
    -0.07
    POCH
    -0.07
    æĸ¹éĿ¢æľī
    -0.06
    å°Ķçī¹
    -0.06
    DIC
    -0.06
    INN
    -0.06
    )))),
    -0.06
    è¿Ļä¸ĢçĤ¹
    -0.06
    POSITIVE LOGITS
    orch
    0.09
    bers
    0.07
    uez
    0.07
    dsn
    0.07
     Siri
    0.07
    jan
    0.07
    acz
    0.06
    urse
    0.06
    bery
    0.06
    onaut
    0.06
    Activations Density 0.006%

    No Known Activations