© 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. 9716
    Prev
    Next
    INDEX
    Explanations

    effort has been put

    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
    oor
    -0.08
    plode
    -0.08
    kest
    -0.08
    ernel
    -0.08
    isser
    -0.08
    åıĬéĻĦåĬł
    -0.08
     Weiterlesen
    -0.07
    æµıè§Ī次æķ°
    -0.07
    ropping
    -0.07
    apiro
    -0.07
    POSITIVE LOGITS
     effort
    0.11
     efforts
    0.09
    çĻ½è´¹
    0.08
    ¹
    0.08
    à¸ļาà¸ģ
    0.08
    ä¸įæģ¯
    0.08
    ä¸įæĩĪ
    0.07
     expended
    0.07
    äºĨä¸Ģçķª
    0.07
     towards
    0.07
    Activations Density 0.045%

    No Known Activations