© 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. 23508
    Prev
    Next
    INDEX
    Explanations

    blogger

    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
    ç§
    -0.09
    æĸĩ件çļĦ
    -0.07
    ä¾Ŀç¨Ģ
    -0.06
    åĨįä¸Ģ次
    -0.06
    getFile
    -0.06
    idia
    -0.06
    ä½IJ
    -0.06
    Äĩ
    -0.06
    ´
    -0.06
     Merke
    -0.06
    POSITIVE LOGITS
    usen
    0.08
    ubu
    0.07
     antim
    0.07
    antar
    0.07
    opath
    0.07
    klen
    0.07
    asin
    0.07
    _att
    0.07
    iams
    0.06
    ieni
    0.06
    Activations Density 0.014%

    No Known Activations