© 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. 8869
    Prev
    Next
    INDEX
    Explanations

    together collectively

    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
    缴æİ¥çĶ¨
    -0.08
    åIJĮæŶè¦ģ
    -0.08
    缴æİ¥ä»İ
    -0.08
    缴æİ¥æĬĬ
    -0.08
    缴æİ¥å°Ĩ
    -0.08
    åIJĮæĹ¶ä¹Łæĺ¯
    -0.08
     oneself
    -0.07
    çĽ¸å¯¹èĢĮè¨Ģ
    -0.07
    缴æİ¥åľ¨
    -0.07
    缴æݥ使çĶ¨
    -0.07
    POSITIVE LOGITS
     together
    0.10
    æŀĦæĪIJäºĨ
    0.10
    -sama
    0.09
     Together
    0.09
    æŀĦæĪIJ
    0.09
    Together
    0.09
    æŀĦæĪIJçļĦ
    0.09
    åħ±åIJĮ
    0.08
    ä½ľçĶ¨ä¸ĭ
    0.08
     collectively
    0.08
    Activations Density 0.044%

    No Known Activations