© 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. 38065
    Prev
    Next
    INDEX
    Explanations

    data availability

    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
    åĬłåħ¥æĶ¶èĹı
    -0.07
     ASSO
    -0.07
    gars
    -0.07
    ä¸ĩå²ģ
    -0.07
    coder
    -0.07
    urant
    -0.07
    æĿĤ
    -0.06
    交éģĵ
    -0.06
    æĽ´åı¯
    -0.06
    ury
    -0.06
    POSITIVE LOGITS
     manuscript
    0.07
    çī¹æѤ
    0.07
     pragma
    0.07
     resultMap
    0.07
     declare
    0.07
    æľ¬äºº
    0.06
    åľ¨æľ¬
    0.06
     abide
    0.06
    ä»ħ代表
    0.06
    è²Ŀ
    0.06
    Activations Density 0.063%

    No Known Activations