© 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. 33252
    Prev
    Next
    INDEX
    Explanations

    is followed by a noun or adjective

    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
    çŃīåħ¶ä»ĸ
    -0.07
     distracting
    -0.07
    æ¯Ķè¾ĥ大
    -0.06
    æ¯ķç«Łæĺ¯
    -0.06
    øy
    -0.06
    åĪ©äºİ
    -0.06
    æīįèĥ½ä¿Ŀè¯ģ
    -0.06
    ÙĪÙĦØ©
    -0.06
    åħĪå°Ĩ
    -0.06
    æīįæĺ¯çľŁæŃ£çļĦ
    -0.06
    POSITIVE LOGITS
    丽èIJį
    0.09
    以ä¸ĭåĩł
    0.09
    以ä¸ĭåĩłç§į
    0.08
    isir
    0.08
    以ä¸ĭæĺ¯ä¸ĢäºĽ
    0.08
    以ä¸ĭåĩłä¸ªæĸ¹éĿ¢
    0.08
     meticulously
    0.08
     ëĭ¤ìĿĮê³¼
    0.08
    BarController
    0.07
    以ä¸ĭåĩłä¸ª
    0.07
    Activations Density 0.010%

    No Known Activations