© 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. 29856
    Prev
    Next
    INDEX
    Explanations

    dates and publications

    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
    饲
    -0.08
    edException
    -0.07
    åİĮ
    -0.06
    éĵ¾
    -0.06
     OCC
    -0.06
     Ech
    -0.06
    adow
    -0.06
    æĭįåĩº
    -0.06
    éķ¿æĮīè¯ĨåĪ«äºĮç»´çłģ
    -0.06
     Eind
    -0.06
    POSITIVE LOGITS
     полÑĮзов
    0.08
    blig
    0.07
    andia
    0.07
    mozilla
    0.07
    allis
    0.07
    壹
    0.07
    loit
    0.07
    ãģĻãģĮ
    0.07
    ä¸Ĭæ·»
    0.07
    peg
    0.07
    Activations Density 0.009%

    No Known Activations