© 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. 39316
    Prev
    Next
    INDEX
    Explanations

    math symbols: - + ) }

    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
    erness
    -0.10
    _INITIALIZER
    -0.08
    çŃ¹
    -0.08
    лаÑĤÑĭ
    -0.08
    imba
    -0.08
     genaus
    -0.08
    ارÛĮ
    -0.08
    igin
    -0.08
    áŀĬáŁĤ
    -0.08
    转账
    -0.08
    POSITIVE LOGITS
    æł¼
    0.07
    è¿Ļ个éģĵçIJĨ
    0.06
    פ×ķת
    0.06
    ÑģÑĤанов
    0.06
    æł¼çļĦ
    0.06
     Campus
    0.06
    åºĶçĶ¨åĪ°
    0.06
    aa
    0.06
     inhib
    0.06
    _throw
    0.06
    Activations Density 0.003%

    No Known Activations