© 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. 17278
    Prev
    Next
    INDEX
    Explanations

    difference or comparison

    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
    åIJĪéĢĤçļĦ
    -0.07
    ä¸Ģå®ļèĥ½
    -0.07
    èī¯å¥½çļĦ
    -0.07
    è¶³å¤ŁçļĦ
    -0.07
    åIJĪæł¼çļĦ
    -0.07
     appropriate
    -0.07
    çĴĢ
    -0.06
    relevant
    -0.06
    çļĦèī¯å¥½
    -0.06
    åĩºèī²çļĦ
    -0.06
    POSITIVE LOGITS
     Whereas
    0.16
     differs
    0.15
     whereas
    0.14
     differed
    0.14
     differ
    0.13
    缸æ¯Ķä¹ĭä¸ĭ
    0.13
    ä¸įåIJĮçļĦæĺ¯
    0.12
     vs
    0.12
     contrasts
    0.12
     Unterschiede
    0.12
    Activations Density 0.032%

    No Known Activations