© 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. 15969
    Prev
    Next
    INDEX
    Explanations

    currency units

    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
    éĿ¢æĹł
    -0.08
    æ»¡çľ¼
    -0.07
    aldas
    -0.07
    åIJijçĿĢ
    -0.07
    iaga
    -0.07
    æĽ²å¼ł
    -0.07
    åľ¨æīĢ
    -0.07
    _GENER
    -0.07
    rdf
    -0.07
    æŃ£å¸¸æĥħåĨµä¸ĭ
    -0.07
    POSITIVE LOGITS
    å®ļä¹ī为
    0.09
     اÙĦÙĪاØŃد
    0.08
    IGIN
    0.08
    asar
    0.07
    ạt
    0.07
    åIJ«éĩijéĩı
    0.07
     defined
    0.07
     Defined
    0.07
    äºĨå¤ļå°ij
    0.07
    çĶ±æĿ¥
    0.07
    Activations Density 0.024%

    No Known Activations