© 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. 64135
    Prev
    Next
    INDEX
    Explanations

    Japanese patent application 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
    ItemClick
    -0.08
    itten
    -0.08
    èī¾çijŀ
    -0.07
    airy
    -0.07
    éªļ
    -0.07
    BUS
    -0.07
    ort
    -0.07
    ারণ
    -0.07
    溪éķĩ
    -0.07
    compression
    -0.07
    POSITIVE LOGITS
    odos
    0.07
    ader
    0.07
    fat
    0.06
    ÄĻt
    0.06
    ODB
    0.06
    骨åŃIJéĩĮ
    0.06
     Sierra
    0.06
    isi
    0.06
    unders
    0.06
    elang
    0.06
    Activations Density 0.001%

    No Known Activations