© 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. 65354
    Prev
    Next
    INDEX
    Explanations

    currency following "of"

    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
    ï¸ı
    -0.07
    ä¹ĭåħī
    -0.07
    ('-
    -0.07
    (({
    -0.06
    =='
    -0.06
    á
    -0.06
    ism
    -0.06
    æĺ¯è¿Ļæł·çļĦ
    -0.06
    (['
    -0.06
    éĤ£ä½łå°±
    -0.06
    POSITIVE LOGITS
    [image
    0.09
    serter
    0.09
    üst
    0.08
    à¹Ģà¸ŀียà¸ĩ
    0.08
    ï½ŀãĢĤ
    0.08
    åĪ©æĸ¯
    0.08
    istere
    0.08
     appunto
    0.08
    udge
    0.08
    änn
    0.08
    Activations Density 0.221%

    No Known Activations