© 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. 21761
    Prev
    Next
    INDEX
    Explanations

    (i) individual, (u) unilateral

    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
    åĴĮæĶ¹åĸĦ
    -0.08
    phan
    -0.08
    è¦ģéĹ»
    -0.08
    大éĥ¨
    -0.07
    uiltin
    -0.07
    ä¸ĩä¸Ī
    -0.07
    uring
    -0.07
    auge
    -0.07
    agi
    -0.07
    urian
    -0.07
    POSITIVE LOGITS
    صاÙĦ
    0.07
    çļĦ梦
    0.07
    engel
    0.06
    okin
    0.06
     Hicks
    0.06
    解
    0.06
     unknow
    0.06
    haft
    0.06
    ä¸ŃæĭĽ
    0.06
    à¸ķà¹Ī
    0.06
    Activations Density 0.002%

    No Known Activations