© 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. 14664
    Prev
    Next
    INDEX
    Explanations

    questions about management

    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
    æĻĤãģ¯
    -0.07
    ä¸İåħ¶å®ĥ
    -0.07
    çļĦ人è¿ĺ
    -0.07
    Õ¸ÖĤ
    -0.07
     Flag
    -0.07
    andung
    -0.07
    lickr
    -0.07
    ãģĵãĤĮãĤĤ
    -0.07
    SUMER
    -0.07
    licant
    -0.07
    POSITIVE LOGITS
    对该
    0.08
    åľ¨ä¸Ĭè¿°
    0.08
    讳
    0.07
    åľ¨è¯¥
    0.07
    对ä¸Ĭè¿°
    0.07
     specifically
    0.06
    Âł
    0.06
    :(
    0.06
    è¿Ļç¬Ķ
    0.06
    малÑĮ
    0.06
    Activations Density 0.179%

    No Known Activations