© 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. 42532
    Prev
    Next
    INDEX
    Explanations

    prohibitions or restrictions

    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
    ä¸į太
    -0.08
    èĢĮéĿŀ
    -0.08
    ÙĦÙģت
    -0.07
    åIJ¸å¼ķäºĨ
    -0.07
     plenty
    -0.07
    çĿ¦
    -0.07
     somewhere
    -0.07
    注æĺİæĿ¥æºIJ
    -0.07
    rather
    -0.07
    inbox
    -0.07
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.16
    ä»»ä½ķå½¢å¼ıçļĦ
    0.16
    以任ä½ķ
    0.13
    ä»»ä½ķ人
    0.13
    åģļä»»ä½ķ
    0.13
    ä»»ä½ķçļĦ
    0.12
    ä»»ä½ķ
    0.12
    åľ¨ä»»ä½ķ
    0.12
    æĽ´ä¸įèĥ½
    0.11
    éļıæĦı
    0.10
    Activations Density 0.086%

    No Known Activations