© 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. 34537
    Prev
    Next
    INDEX
    Explanations

    numbers followed by units or descriptions

    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
     fameux
    -0.07
    派驻
    -0.07
    edBy
    -0.07
    alism
    -0.07
    evt
    -0.06
     others
    -0.06
    gebracht
    -0.06
    elsÅij
    -0.06
    бÑĢан
    -0.06
    ë´
    -0.06
    POSITIVE LOGITS
    (?)
    0.09
    çļĦæĸ¹å¼ıæĿ¥
    0.08
     (=
    0.08
     (!
    0.08
     (?)
    0.08
    ITIONAL
    0.08
    èĢĮä¸įè§ģ
    0.08
    æĸ¹å¼ı使çĶ¨
    0.07
    0.07
    è¿Ļä¹Īå¤ļçļĦ
    0.07
    Activations Density 0.266%

    No Known Activations