© 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. 47318
    Prev
    Next
    INDEX
    Explanations

    degrees, mph, statistics, numbers

    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
    ÙĪتر
    -0.07
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.07
    é¹ıé£ŀ
    -0.06
    abet
    -0.06
     übernehmen
    -0.06
    /window
    -0.06
     matched
    -0.06
    ysin
    -0.06
    åĴ
    -0.06
    é¢ł
    -0.06
    POSITIVE LOGITS
    表æĺİ
    0.12
    è¿Ļ表æĺİ
    0.12
     indicating
    0.10
     qualifies
    0.10
     indicative
    0.10
    å±ŀäºİ
    0.10
    ä»İèĢĮ使
    0.10
     indicates
    0.10
     defines
    0.10
    è¿Ļ说æĺİ
    0.10
    Activations Density 0.173%

    No Known Activations