© 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. 63084
    Prev
    Next
    INDEX
    Explanations

    possessive ('s) followed by nouns

    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
    ìį¨
    -0.08
    ä¸įå®ĮçļĦ
    -0.08
    åħ¶ä¸ŃçļĦ
    -0.08
    Å¡n
    -0.07
    Ùĭ
    -0.07
    äºĨ
    -0.07
    zie
    -0.07
    Ùį
    -0.07
    åIJİæŀľ
    -0.07
    人群
    -0.07
    POSITIVE LOGITS
     behalf
    0.12
     own
    0.11
    sing
    0.09
     ability
    0.09
    innen
    0.09
     usual
    0.08
    sed
    0.08
    /her
    0.08
    æĶ¾çŁ¢
    0.08
    缸è¾ħ缸æĪIJ
    0.08
    Activations Density 0.228%

    No Known Activations