© 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. 45211
    Prev
    Next
    INDEX
    Explanations

    relative comparison and time

    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
    è²´
    -0.08
    çİ°
    -0.07
    ovid
    -0.07
    ä¹Łç½¢
    -0.07
    gis
    -0.07
    imu
    -0.07
    å½¢åĬ¿ä¸ĭ
    -0.07
    elly
    -0.07
    è´µ
    -0.07
    áĥĴáĥĺ
    -0.07
    POSITIVE LOGITS
    çļĦä¸įæĺ¯
    0.08
    /reference
    0.08
    æľĶ
    0.08
    ãģĤãģı
    0.07
    기ì¤Ģ
    0.07
    ศูà¸Ļยà¹Įà¸ģลาà¸ĩ
    0.07
    åıĤèĢĥ
    0.07
    åºĵ
    0.07
    èµĦæºIJç½ij
    0.06
    Reference
    0.06
    Activations Density 0.013%

    No Known Activations