© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 22971
    Prev
    Next
    INDEX
    Explanations

    mathematical and scientific terms

    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
    xmlns
    -0.06
    neu
    -0.06
     Ø´ÙĨا
    -0.06
    è¿Ļä¸Ģ个
    -0.06
    第ä¸ī产ä¸ļ
    -0.06
    ennie
    -0.06
    situ
    -0.06
    ä¸ĩæĪ·
    -0.06
    ActionResult
    -0.06
     situ
    -0.06
    POSITIVE LOGITS
    æİĸ
    0.10
    usher
    0.08
    .nc
    0.08
    æĺ¯ä½ķ
    0.07
    夷
    0.07
    æīĢçĶ¨
    0.07
    ä½ľä¸ļæŶ
    0.07
    itado
    0.07
    atera
    0.07
    swer
    0.07
    Activations Density 0.021%

    No Known Activations