© 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. 47106
    Prev
    Next
    INDEX
    Explanations

    time durations

    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
    æĢ»æľīä¸Ģ天
    -0.08
     years
    -0.07
    åįģäºĮå¹´
    -0.07
    使çĶ¨å¹´éĻIJ
    -0.07
    Years
    -0.07
    å¹´éĻIJ
    -0.07
    æħ¢æĢ§
    -0.07
     Years
    -0.07
    ä¸ĥå¹´
    -0.07
     lifelong
    -0.07
    POSITIVE LOGITS
    临æŶ
    0.09
    æĢ¥
    0.09
    çŀ¬æģ¯
    0.08
    éĺħè¯»æľ¬æĸĩ
    0.08
    æĢ¥è¯Ĭ
    0.07
    aval
    0.07
    onde
    0.07
    lies
    0.07
    hil
    0.07
    yan
    0.07
    Activations Density 0.972%

    No Known Activations