© 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. 10621
    Prev
    Next
    INDEX
    Explanations

    implementation details

    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
    oken
    -0.09
    rah
    -0.06
    禧
    -0.06
    agram
    -0.06
    ÙIJÙijÙĨ
    -0.06
    åĪ°é«ĺ
    -0.06
     Pokemon
    -0.06
    à§įতà§ģ
    -0.06
    åįĬ天
    -0.06
    ãĥĥãĤ¿ãĥ¼
    -0.06
    POSITIVE LOGITS
    å¹¢
    0.07
    羣æŃ£æĦıä¹īä¸ĬçļĦ
    0.07
    Hex
    0.07
    ä¸ĩä¸Ī
    0.07
    æīİæīİå®ŀ
    0.07
    ÃĹ</
    0.07
    è±ĨèħIJ
    0.07
    vf
    0.06
    æ²¹æĢ§
    0.06
     ÄIJạo
    0.06
    Activations Density 0.017%

    No Known Activations