© 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. 20039
    Prev
    Next
    INDEX
    Explanations

    market value changes

    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
    éľĢè¦ģåĩĨå¤ĩ
    -0.07
    ημα
    -0.07
    该å±Ģ
    -0.07
     Untersch
    -0.07
    UNC
    -0.07
    éĻIJåĪ¶æ¶Īè´¹
    -0.07
    .Logic
    -0.07
     impro
    -0.07
    å·¥åķĨ注åĨĮåı·
    -0.07
    uncul
    -0.07
    POSITIVE LOGITS
     changes
    0.09
     Changes
    0.08
    Changes
    0.08
    æ³¢åĬ¨
    0.08
    åıĺåĮĸ
    0.07
    åıĺåĬ¨
    0.07
     swings
    0.07
    _changes
    0.07
     unreal
    0.07
    åıĺåĮĸçļĦ
    0.07
    Activations Density 0.001%

    No Known Activations