© 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. 46670
    Prev
    Next
    INDEX
    Explanations

    personally and professionally

    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
    éĶĻ误æĪĸ
    -0.12
    å·¥ä½ľæĪĸ
    -0.12
    æĢ§æĪĸ
    -0.10
    ãģĵãģ¨ãĤĦ
    -0.09
    åĽ¾çīĩæĪĸ
    -0.09
    æĸĩ件æĪĸ
    -0.09
    人æĪĸ
    -0.09
    æĬķèµĦæĪĸ
    -0.09
    ear
    -0.09
    å¤įåĪ¶æĪĸ
    -0.09
    POSITIVE LOGITS
     alike
    0.14
    两æĸ¹éĿ¢
    0.10
     zugleich
    0.09
     दà¥ĭनà¥ĭà¤Ĥ
    0.09
    çļĦåıĮéĩį
    0.09
     gleicher
    0.09
    缸ç»ĵåIJĪ
    0.09
    缸ç»ĵåIJĪçļĦ
    0.09
    åıĮéĩį
    0.09
    两ä¸į误
    0.08
    Activations Density 0.380%

    No Known Activations