© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14114
    Prev
    Next
    INDEX
    Explanations

    studies are presented

    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
    åı¥è¯Ŀ说
    -0.08
    åĽ¢ç»ĵä¸Ģèĩ´
    -0.08
    æ´»åĬ¨çŃī
    -0.08
    Tho
    -0.08
    ï¼Łï¼ī
    -0.08
    NullException
    -0.08
    igno
    -0.07
     обаÑĩе
    -0.07
    ä¿¡æģ¯çŃī
    -0.07
    ãģĺãĤģãģ¦
    -0.07
    POSITIVE LOGITS
    åħ¶ä¸Ń
    0.08
    habit
    0.07
    .
    0.07
    ãĢĤ
    0.07
    åħ¶éĹ´
    0.06
    纪
    0.06
    ä»£æĽ¿
    0.06
    ä¸ĢåºĶ俱åħ¨
    0.06
    èĮ
    0.06
     instead
    0.06
    Activations Density 0.630%

    No Known Activations