© 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. 46500
    Prev
    Next
    INDEX
    Explanations

    disfavored, favor, best-interest

    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¸įçŁ¥éģĵèĩªå·±
    -0.07
     اÙĦعÙħ
    -0.07
    лок
    -0.06
    èĩªæĪij管çIJĨ
    -0.06
    ieux
    -0.06
    å·®çļĦ
    -0.06
    DI
    -0.06
    è¿Ħ
    -0.06
    diy
    -0.06
    way
    -0.06
    POSITIVE LOGITS
    æľīåĪ©äºİ
    0.10
    æľīåĬ©äºİ
    0.09
    asca
    0.08
    åĢ¾åIJijäºİ
    0.08
    favor
    0.08
     interpret
    0.08
    æĺ¯ä¸ºäºĨ
    0.08
    åİŁåĪĻ
    0.08
    åĢ¾åIJij
    0.08
    ERIA
    0.08
    Activations Density 0.007%

    No Known Activations