© 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. 4077
    Prev
    Next
    INDEX
    Explanations

    possessive "'s"

    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
    ä¸ĢåĪĩéĥ½æĺ¯
    -0.08
    ÙİØ©Ùĭ
    -0.08
    æĢ§æĺ¯
    -0.08
    ìŀ¥ìĿĢ
    -0.08
    æķ´ä¸ªè¿ĩç¨ĭ
    -0.07
    å¹´åľ¨
    -0.07
    å¹´æĺ¯
    -0.07
    åĨħ容çĶ±
    -0.07
    ãģĭãģ¯
    -0.07
    æĢ§çŃī
    -0.07
    POSITIVE LOGITS
    's
    0.22
    ’s
    0.20
    ìĿĺ
    0.13
    ‘s
    0.13
    ´s
    0.12
    ëĵ¤ìĿĺ
    0.11
    ()'
    0.11
    们çļĦ
    0.10
    åĦ¿çļĦ
    0.10
    `s
    0.10
    Activations Density 0.440%

    No Known Activations