© 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. 32194
    Prev
    Next
    INDEX
    Explanations

    Pepsi Cola, United States

    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
    toa
    -0.08
    γÏģαμμα
    -0.08
    à¹īว
    -0.08
    warzys
    -0.08
    ä¸įåı¯æĢĿè®®
    -0.08
    êµī
    -0.08
    kof
    -0.08
    ä¹IJä¹İ
    -0.08
    issy
    -0.08
    ubbo
    -0.08
    POSITIVE LOGITS
     dag
    0.07
    ³
    0.06
    NP
    0.06
    aine
    0.06
    elor
    0.06
     that
    0.06
    ì¹¼
    0.06
     long
    0.06
    t
    0.06
    æŦ
    0.05
    Activations Density 0.001%

    No Known Activations