© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 47408
    Prev
    Next
    INDEX
    Explanations

    first, second

    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
    ä¹Ŀ大
    -0.08
    iente
    -0.07
    ientes
    -0.07
    iach
    -0.07
    åĢį
    -0.07
    å¤ļå°ij次
    -0.07
    ède
    -0.07
    équ
    -0.07
    ibox
    -0.07
    æĸ°æĺŁ
    -0.07
    POSITIVE LOGITS
     arbitrarily
    0.08
    ä»»æĦı
    0.07
    âĢ¦and
    0.07
    ä»İä¸Ģ个
    0.07
     two
    0.07
    DirectoryName
    0.06
     arbitrary
    0.06
    æĦıè§ģåĴĮ建议
    0.06
    第
    0.06
     Arbitrary
    0.06
    Activations Density 0.041%

    No Known Activations