© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34791
    Prev
    Next
    INDEX
    Explanations

    single, decisive, winner

    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
    Resize
    -0.08
    orde
    -0.07
    å¢ŀ
    -0.07
    antin
    -0.07
    ä¿ĿçķĻ
    -0.07
     ÄijÃł
    -0.07
    æķ¬
    -0.07
    ãĤĴæ®ĭ
    -0.07
     Pró
    -0.07
    BufferData
    -0.07
    POSITIVE LOGITS
    åįķä¸Ģ
    0.15
     single
    0.14
    åįķä¸ĢçļĦ
    0.14
     tunggal
    0.14
    åĸ®ä¸Ģ
    0.13
    Single
    0.13
    /single
    0.13
     SINGLE
    0.13
    single
    0.12
     Single
    0.12
    Activations Density 0.111%

    No Known Activations