© 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. 26113
    Prev
    Next
    INDEX
    Explanations

    possessive marker followed by diverse 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
    管çĶ¨
    -0.08
    佼佼èĢħ
    -0.07
    æĽĻ
    -0.07
    åĴĮèĥ½åĬĽ
    -0.07
    çļĦå®īæİĴ
    -0.06
    åıĤä¸İåħ¶ä¸Ń
    -0.06
    оÑĩÑĮ
    -0.06
    Õ©
    -0.06
    责任追究
    -0.06
    çłĶ究表æĺİ
    -0.06
    POSITIVE LOGITS
    apsed
    0.08
    æĪĸåħ¶
    0.08
    æīĢ欲
    0.08
    adem
    0.07
    èµĸ以
    0.07
    ãģ£ãģ¨
    0.07
    owi
    0.06
    адÑĮ
    0.06
    å¼ķ以为
    0.06
    æī¬æī¬
    0.06
    Activations Density 0.063%

    No Known Activations