© 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. 10330
    Prev
    Next
    INDEX
    Explanations

    food or dietary terms

    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
     ׾׳×ķ
    -0.07
    tram
    -0.07
    ABL
    -0.07
    ÅĽÄĩ
    -0.07
    ÑĢене
    -0.07
    çŃīåİŁåĽł
    -0.07
    Bợi
    -0.07
    ouro
    -0.07
    ÙħÙĨÙĬ
    -0.07
    çĶ¸
    -0.07
    POSITIVE LOGITS
    -related
    0.07
    èĢĮä¸įæĺ¯
    0.07
    èĢĮéĿŀ
    0.07
    æīį对
    0.07
    åĩĨ
    0.06
    çŁ¥éģĵåIJĹ
    0.06
    缸åºĶçļĦ
    0.06
    ula
    0.06
     statt
    0.06
     stessa
    0.06
    Activations Density 0.076%

    No Known Activations