© 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. 27561
    Prev
    Next
    INDEX
    Explanations

    Health and appliances

    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
    ForResult
    -0.07
    olars
    -0.07
     normalt
    -0.07
    oom
    -0.07
    绣
    -0.07
     اÙĦدرجة
    -0.07
    oarece
    -0.07
    æľĢåħĪ
    -0.06
    ystems
    -0.06
    -FIRST
    -0.06
    POSITIVE LOGITS
    é«ĺ人
    0.07
    çıĪ
    0.07
    ä¿ĿæĮģé«ĺ度
    0.07
    ç¯Ŀ
    0.07
    ä¸įè¦ģå¿ĺäºĨ
    0.07
    usst
    0.06
    æĥ³æĬĬ
    0.06
    æĥ³çľĭ
    0.06
    认缴åĩºèµĦ
    0.06
    åIJĥçĤ¹
    0.06
    Activations Density 0.007%

    No Known Activations