© 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. 50709
    Prev
    Next
    INDEX
    Explanations

    "button" or "option" following punctuation

    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
    ziel
    -0.08
    cek
    -0.08
    ä¸įåı¯åıĬ
    -0.07
    _styles
    -0.07
    zial
    -0.07
    entai
    -0.07
    apol
    -0.07
    amil
    -0.07
    atel
    -0.07
    亨
    -0.07
    POSITIVE LOGITS
    æĸ°åĬłåĿ¡
    0.08
    åĬłæĭ¿å¤§
    0.08
    åĭĩå¾Ģ缴åīį
    0.07
     section
    0.07
    顾åIJįæĢĿä¹ī
    0.07
    ãĢģ“
    0.07
    ettino
    0.06
    ëĿ¼ëĬĶ
    0.06
    缸è¾ħ缸æĪIJ
    0.06
    inan
    0.06
    Activations Density 0.214%

    No Known Activations