© 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. 18063
    Prev
    Next
    INDEX
    Explanations

    vs. / versus

    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
    æĪĸåħ¶ä»ĸ
    -0.07
    æĢ»ä½ĵä¸Ĭ
    -0.07
    æĪĸåħ¶å®ĥ
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
     wen
    -0.07
    ãĤĪãģĨãģª
    -0.07
    asley
    -0.07
    ãĤ¥
    -0.07
    æĪĸçĶ¨
    -0.06
    emo
    -0.06
    POSITIVE LOGITS
    çļĦæ¦Ĥ念
    0.15
     vs
    0.12
     concept
    0.12
     versus
    0.11
    æ¦Ĥ念
    0.11
    ãģ¨ãģĦãģĨè¨Ģèijī
    0.11
     ÙħÙģÙĩÙĪÙħ
    0.10
    çļĦåIJ«ä¹ī
    0.10
    æ¦Ĥ念çļĦ
    0.10
    çļĦå®ļä¹ī
    0.09
    Activations Density 0.147%

    No Known Activations