© 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. 20478
    Prev
    Next
    INDEX
    Explanations

    but, although, unless

    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
    ноÑģ
    -0.08
    æīĢ以å½ĵ
    -0.08
    sts
    -0.08
    оÑģÑĤÑĢе
    -0.08
    æķħ
    -0.08
    gaste
    -0.08
    áŀ¼áŀľ
    -0.08
    注æĦıäºĨ
    -0.08
    ÐĹÐIJ
    -0.08
    portun
    -0.07
    POSITIVE LOGITS
    å¦ĤæѤä¸ĢæĿ¥
    0.08
    æĺİæĺİæĺ¯
    0.08
    ung
    0.08
    æĪĸèĢħæĺ¯
    0.07
     contrad
    0.07
    è¿Ļæł·çļĦè¯Ŀ
    0.07
    éĤ£æł·çļĦ
    0.07
    æĺİæĺİ
    0.07
    è¿Ļä¹Ī说
    0.07
    ord
    0.06
    Activations Density 0.022%

    No Known Activations