© 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. 14927
    Prev
    Next
    INDEX
    Explanations

    existence questions

    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
    è¦ģç´§
    -0.07
    å¾Īéĩįè¦ģçļĦ
    -0.07
    èѬå¦Ĥ
    -0.07
     wichtigsten
    -0.07
    第ä¸Ģ件äºĭ
    -0.07
    æĺ¯éĿŀ常éĩįè¦ģçļĦ
    -0.07
    éĩįè¦ģ讲è¯Ŀ
    -0.07
     обÑıзаÑĤелÑĮном
    -0.07
    vem
    -0.07
    æĺ¯å¾Īéĩįè¦ģçļĦ
    -0.07
    POSITIVE LOGITS
    符åIJĪæĿ¡ä»¶çļĦ
    0.07
    æľīæѤ
    0.07
     satisfactory
    0.07
     satisfying
    0.07
     any
    0.07
    符åIJĪæĿ¡ä»¶
    0.07
    ater
    0.07
     impossible
    0.07
    ä¹Łä¸įåı¯èĥ½
    0.07
     perfect
    0.07
    Activations Density 0.045%

    No Known Activations