© 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. 20455
    Prev
    Next
    INDEX
    Explanations

    vector space and dimension

    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
    累累
    -0.08
     cardÃŃ
    -0.08
    åĴĢåļ¼
    -0.08
    çļĦä¸Ģé¢Ĺ
    -0.08
    olat
    -0.08
    isle
    -0.08
    æĺ¯ä¸Ģé¢Ĺ
    -0.08
     Schuh
    -0.07
    éŀŃçĤ®
    -0.07
    两é¢Ĺ
    -0.07
    POSITIVE LOGITS
    Vectors
    0.10
     vectors
    0.09
    _vectors
    0.08
    /vector
    0.07
     vector
    0.07
    宿
    0.07
    æŁĵ
    0.07
    .Vector
    0.07
     Algebra
    0.07
    igon
    0.07
    Activations Density 0.026%

    No Known Activations